Tootfinder

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural
Rid…

Estimating Spatially Resolved Radiation Fields Using Neural Networks
Felix Lehner, Pasquale Lombardo, Susana Castillo, Oliver Hupe, Marcus Magnor
https://arxiv.org/abs/2512.17654 https://arxiv.org/pdf/2512.17654 https://arxiv.org/html/2512.17654
arXiv:2512.17654v1 Announce Type: new
Abstract: We present an in-depth analysis on how to build and train neural networks to estimate the spatial distribution of scattered radiation fields for radiation protection dosimetry in medical radiation fields, such as those found in Interventional Radiology and Cardiology. Therefore, we present three different synthetically generated datasets with increasing complexity for training, using a Monte-Carlo Simulation application based on Geant4. On those datasets, we evaluate convolutional and fully connected architectures of neural networks to demonstrate which design decisions work well for reconstructing the fluence and spectra distributions over the spatial domain of such radiation fields. All used datasets as well as our training pipeline are published as open source in separate repositories.
toXiv_bot_toot

Distributionally robust approximation property of neural networks
Mihriban Ceylan, David J. Pr\"omel
https://arxiv.org/abs/2510.09177 https://arxiv.or…

Distributionally robust approximation property of neural networks
The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby extending classical universal approximation theorems even beyond the traditional $L^p$-setting. The covered classes of neural networks include widely used architectures like feedforward neural networks with non-polynomial activation functions, deep narrow netw…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

Lecture Notes on Verifying Graph Neural Networks
Fran\c{c}ois Schwarzentruber
https://arxiv.org/abs/2510.11617 https://arxiv.org/pdf/2510.11617

Lecture Notes on Verifying Graph Neural Networks
In these lecture notes, we first recall the connection between graph neural networks, Weisfeiler-Lehman tests and logics such as first-order logic and graded modal logic. We then present a modal logic in which counting modalities appear in linear inequalities in order to solve verification tasks on graph neural networks. We describe an algorithm for the satisfiability problem of that logic. It is inspired from the tableau method of vanilla modal logic, extended with reasoning in quantifier-free…

Hybrid Ridgelet Deep Neural Networks for Data-Driven Arbitrage Strategies
Bahadur Yadav, Sanjay Kumar Mohanty
https://arxiv.org/abs/2510.10599 https://arxi…

Hybrid Ridgelet Deep Neural Networks for Data-Driven Arbitrage Strategies
In this study, we propose a novel model framework that integrates deep neural networks with the Ridgelet Transform. The Ridgelet Transform on Borel measurable functions is used for arbitrage detection on high-dimensional sparse structures. This transform also enhances the expressive power of neural networks, enabling them to capture complex and high-dimensional market structures. Theoretically, we determine profitable trading strategies by optimizing hybrid ridgelet deep neural networks. Furthe…

🤖 Kremlin and AI: how Russian propaganda attacks neural networks: https://benborges.xyz/2025/10/19/kremlin-and-ai-how-russian.html

Triangular neural synchronization patterns in visual impairment: A comprehensive case series exploring multi-node network dynamics and the Neural Triangle Index (NTI) https://www.

Triangular Neural Synchronization Patterns in Visual Impairment: A Comprehensive Case Series Exploring Multi-node Network Dynamics and the Neural Triangle Index
Background: Compensatory neural plasticity in visual impairment involves complex reorganization of multi-node networks that goes beyond conventional bilateral connection analysis. Triangular synchronization patterns, representing coordinated activity among three cortical sites simultaneously, remain unexplored despite their potential to reveal fundamental mechanisms underlying compensatory neuroplasticity. Objective: This study aimed to conduct a case series examining triangular neural synchro…

PromptFlow: Training Prompts Like Neural Networks
Jingyi Wang, Hongyuan Zhu, Ye Niu, Yunhui Deng
https://arxiv.org/abs/2510.12246 https://arxiv.org/pdf/251…

PromptFlow: Training Prompts Like Neural Networks
Large Language Models (LLMs) have demonstrated profound impact on Natural Language Processing (NLP) tasks. However, their effective deployment across diverse domains often require domain-specific adaptation strategies, as generic models may underperform when faced with specialized data distributions. Recent advances in prompt engineering (PE) offer a promising alternative to extensive retraining by refining input instructions to align LLM outputs with task objectives. This paradigm has emerged …

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
Jiachen Li, Bang Wu, Xiaoyu Xia, Xiaoning Liu, Xun Yi, Xiuzhen Zhang
https://arxiv.org/abs/2510.06629 …

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited attention. Existing defense methods developed for ANNs perform poorly or can be easily bypassed in SNNs due to their event-driven and temporal dependencies. This paper identifies the key blockers that hinder traditional backdoor defenses in SNNs and proposes …

The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
Takehiro Ishikawa
https://arxiv.org/abs/2510.08591

The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks
Recent advancements in QML and SNNs have generated considerable excitement, promising exponential speedups and brain-like energy efficiency to revolutionize AI. However, this paper argues that they are unlikely to displace DNNs in the near term. QML struggles with adapting backpropagation due to unitary constraints, measurement-induced state collapse, barren plateaus, and high measurement overheads, exacerbated by the limitations of current noisy intermediate-scale quantum hardware, overfitting…

Bayesian Topological Convolutional Neural Nets
Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas, David L. Boothe Jr., Vasileios Maroulas
https://arxiv.org/abs/2510.11704 ht…

Bayesian Topological Convolutional Neural Nets
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to quantify the uncertainty of their predictions. To address these concerns, we propose a new Bayesian topological CNN that promotes a novel interplay between topology-aware learning and Bayesian sampling. Specifically, it utilizes information from important ma…

Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs
Georges Aad, Raphael Bertrand, Lauri Laatu, Emmanuel Monnier, Arno Straessner, Nairit Sur, Johann C. Voigt
https://arxiv.org/abs/2510.11469

Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs
A study of neural network architectures for the reconstruction of the energy deposited in the cells of the ATLAS liquid-argon calorimeters under high pile-up conditions expected at the HL-LHC is presented. These networks are designed to run on the FPGA-based readout hardware of the calorimeters under strict size and latency constraints. Several architectures, including Dense, Recurrent (RNN), and Convolutional (CNN) neural networks, are optimised using a Bayesian procedure that balances energy …

Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
Giacomo Dimarco, Federica Ferrarese, Lorenzo Pareschi
https://arxiv.org/abs/2510.09192

Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
In this work, we propose a data augmentation strategy aimed at improving the training phase of neural networks and, consequently, the accuracy of their predictions. Our approach relies on generating synthetic data through a suitable compartmental model combined with the incorporation of uncertainty. The available data are then used to calibrate the model, which is further integrated with deep learning techniques to produce additional synthetic data for training. The results show that neural net…

CoNet-Rx: Collaborative Neural Networks for OFDM Receivers
Mohanad Obeed, Ming Jian
https://arxiv.org/abs/2510.12739 https://arxiv.org/pdf/2510.12739

CoNet-Rx: Collaborative Neural Networks for OFDM Receivers
Deep learning (DL) based methods for orthogonal frequency division multiplexing (OFDM) radio receivers demonstrated higher signal detection performance compared to the traditional receivers. However, the existing DL-based models, usually adapted from computer vision, aren't well suited for wireless communications. These models require high computational resources and memory, and have significant inference delays, limiting their use in resource-constrained settings. Additionally, reducing networ…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
Haoran He
https://arxiv.org/abs/2510.11891 https://ar…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination and high mobility issues that harm system reliability. The proposed DNN architecture includes multi-layer perceptrons with ReLU activation, 3 hidden layers (256, 128, 64 neurons respectively), uses Adam optimizer (learning rate 1e-4) and MSE loss function. I…

Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
Yuri Calleo
https://arxiv.org/abs/2512.17696 https://arxiv.org/pdf/2512.17696 https://arxiv.org/html/2512.17696
arXiv:2512.17696v1 Announce Type: new
Abstract: The modeling of high-dimensional spatio-temporal processes presents a fundamental dichotomy between the probabilistic rigor of classical geostatistics and the flexible, high-capacity representations of deep learning. While Gaussian processes offer theoretical consistency and exact uncertainty quantification, their prohibitive computational scaling renders them impractical for massive sensor networks. Conversely, modern transformer architectures excel at sequence modeling but inherently lack a geometric inductive bias, treating spatial sensors as permutation-invariant tokens without a native understanding of distance. In this work, we propose a spatially-informed transformer, a hybrid architecture that injects a geostatistical inductive bias directly into the self-attention mechanism via a learnable covariance kernel. By formally decomposing the attention structure into a stationary physical prior and a non-stationary data-driven residual, we impose a soft topological constraint that favors spatially proximal interactions while retaining the capacity to model complex dynamics. We demonstrate the phenomenon of ``Deep Variography'', where the network successfully recovers the true spatial decay parameters of the underlying process end-to-end via backpropagation. Extensive experiments on synthetic Gaussian random fields and real-world traffic benchmarks confirm that our method outperforms state-of-the-art graph neural networks. Furthermore, rigorous statistical validation confirms that the proposed method delivers not only superior predictive accuracy but also well-calibrated probabilistic forecasts, effectively bridging the gap between physics-aware modeling and data-driven learning.
toXiv_bot_toot

Adaptive Decoding via Hierarchical Neural Information Gradients in Mouse Visual Tasks
Jingyi Feng, Xiang Feng
https://arxiv.org/abs/2510.09451 https://arxi…

Adaptive Decoding via Hierarchical Neural Information Gradients in Mouse Visual Tasks
Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs) have played a significant role as tools for mining the core features of complex data. However, most methods often overlook the dynamic generation process of neural data, such as hierarchical brain's visual data, within the brain's structure. In the decoding …

Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
Xiucheng Wang, Zien Wang, Nan Cheng, Wenchao Xu, Wei Quan, Xuemin Shen
https://arxiv.org/abs/2510.11109

Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
The increase of bandwidth-intensive applications in sixth-generation (6G) wireless networks, such as real-time volumetric streaming and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either computationally prohibitive or structurally rigid, and they often fail to support heterogeneous user demands, leading to suboptimal resource …

Accelerating Inference for Multilayer Neural Networks with Quantum Computers
Arthur G. Rattew, Po-Wei Huang, Naixu Guo, Lirand\"e Pira, Patrick Rebentrost
https://arxiv.org/abs/2510.07195

Accelerating Inference for Multilayer Neural Networks with Quantum Computers
Fault-tolerant Quantum Processing Units (QPUs) promise to deliver exponential speed-ups in select computational tasks, yet their integration into modern deep learning pipelines remains unclear. In this work, we take a step towards bridging this gap by presenting the first fully-coherent quantum implementation of a multilayer neural network with non-linear activation functions. Our constructions mirror widely used deep learning architectures based on ResNet, and consist of residual blocks with m…

A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
Hagen Holthusen, Ellen Kuhl
https://arxiv.org/abs/2510.04187 https://arxiv.o…

A Complement to Neural Networks for Anisotropic Inelasticity at Finite Strains
We propose a complement to constitutive modeling that augments neural networks with material principles to capture anisotropy and inelasticity at finite strains. The key element is a dual potential that governs dissipation, consistently incorporates anisotropy, and-unlike conventional convex formulations-satisfies the dissipation inequality without requiring convexity. Our neural network architecture employs invariant-based input representations in terms of mixed elastic, inelastic and struct…

Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
Caden Ginter, Kamal Choudhary, Subhasish Mandal
https://arxiv.org/abs/2510.08738

Accelerated prediction of dielectric functions in solar cell materials with graph neural networks
We present an atomistic line graph neural network (ALIGNN) model for predicting dielectric functions directly from crystal structures. Trained on $\sim$7000 dielectric functions from the JARVIS-DFT database computed with a meta-GGA exchange-correlation functional, the model accurately reproduces spectral features, including peak intensities and overall line shapes, while enabling efficient high-throughput screening. Applied to the recently developed Alexandria materials database, containing ove…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

OptimES: Optimizing Federated Learning Using Remote Embeddings for Graph Neural Networks
Pranjal Naman, Yogesh Simmhan
https://arxiv.org/abs/2509.22922 https://

OptimES: Optimizing Federated Learning Using Remote Embeddings for Graph Neural Networks
Graph Neural Networks (GNNs) have experienced rapid advancements in recent years due to their ability to learn meaningful representations from graph data structures. However, in most real-world settings, such as financial transaction networks and healthcare networks, this data is localized to different data owners and cannot be aggregated due to privacy concerns. Federated Learning (FL) has emerged as a viable machine learning approach for training a shared model that iteratively aggregates loc…

Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks
Hai Siong Tan
https://arxiv.org/abs/2509.24327 https://arxiv.org/pdf/250…

Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks
We examine the use of a novel variant of Physics-Informed Neural Networks to predict cosmological parameters from recent supernovae and baryon acoustic oscillations (BAO) datasets. Our machine learning framework generates uncertainty estimates for target variables and the inferred unknown parameters of the underlying PDE descriptions. Built upon a hybrid of the principles of Evidential Deep Learning, Physics-Informed Neural Networks, Bayesian Neural Networks and Gaussian Processes, our model en…

VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by Higher-SNR Virtual Microphone Arrays
Shulin He, Zhong-Qiu Wang
https://arxiv.org/abs/2510.08914 https://

VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by Higher-SNR Virtual Microphone Arrays
Blind speech separation (BSS) aims to recover multiple speech sources from multi-channel, multi-speaker mixtures under unknown array geometry and room impulse responses. In unsupervised setup where clean target speech is not available for model training, UNSSOR proposes a mixture consistency (MC) loss for training deep neural networks (DNN) on over-determined training mixtures to realize unsupervised speech separation. However, when the number of microphones of the training mixtures decreases, …

Intelligent backpropagated neural networks application on Couette-Poiseuille flow of variable viscosity in a composite porous channel filled with an anisotropic porous layer
Timir Karmakar, Amrita Mandal
https://arxiv.org/abs/2510.08745

Intelligent backpropagated neural networks application on Couette-Poiseuille flow of variable viscosity in a composite porous channel filled with an anisotropic porous layer
This study examines Couette-Poiseuille flow of variable viscosity within a channel that is partially filled with a porous medium. To enhance its practical relevance, we assume that the porous medium is anisotropic with permeability varying in all directions, making it a positive semidefinite matrix in the momentum equation. We assume the Navier-Stokes equations govern the flow in the free flow region, while the Brinkman-Forchheimer-extended Darcy's equation governs the flow inside the porous me…

Data-Driven Adaptive PID Control Based on Physics-Informed Neural Networks
Junsei Ito, Yasuaki Wasa
https://arxiv.org/abs/2510.04591 https://arxiv.org/pdf/…

Data-Driven Adaptive PID Control Based on Physics-Informed Neural Networks
This article proposes a data-driven PID controller design based on the principle of adaptive gain optimization, leveraging Physics-Informed Neural Networks (PINNs) generated for predictive modeling purposes. The proposed control design method utilizes gradients of the PID gain optimization, achieved through the automatic differentiation of PINNs, to apply model predictive control using a cost function based on tracking error and control inputs. By optimizing PINNs-based PID gains, the method ac…

Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators
Sven Dummer, Tjeerd Jan Heeringa, Jos\'e A. Iglesias
https://arxiv.org/abs/2509.26371 https:…

Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators
Recently, there has been growing interest in characterizing the function spaces underlying neural networks. While shallow and deep scalar-valued neural networks have been linked to scalar-valued reproducing kernel Banach spaces (RKBS), $\R^d$-valued neural networks and neural operator models remain less understood in the RKBS setting. To address this gap, we develop a general definition of vector-valued RKBS (vv-RKBS), which inherently includes the associated reproducing kernel. Our constructio…

Triangular neural synchronization patterns in visual impairment https://www.cureus.com/articles/409884-triangular-neural-synchronization-patterns-i…

Triangular Neural Synchronization Patterns in Visual Impairment: A Comprehensive Case Series Exploring Multi-node Network Dynamics and the Neural Triangle Index
Background: Compensatory neural plasticity in visual impairment involves complex reorganization of multi-node networks that goes beyond conventional bilateral connection analysis. Triangular synchronization patterns, representing coordinated activity among three cortical sites simultaneously, remain unexplored despite their potential to reveal fundamental mechanisms underlying compensatory neuroplasticity. Objective: This study aimed to conduct a case series examining triangular neural synchro…

Identification of molecular line emission using Convolutional Neural Networks
Nina Kessler, Timea Csengeri, David Cornu, Sylvain Bontemps, Laure Bouscasse
https://arxiv.org/abs/2510.09119

Identification of molecular line emission using Convolutional Neural Networks
Complex organic molecules (COMs) are observed to be abundant in various astrophysical environments, in particular toward star forming regions they are observed both toward protostellar envelopes as well as shocked regions. Emission spectrum especially of heavier COMs may consists of up to hundreds of lines, where line blending hinders the analysis. However, identifying the molecular composition of the gas leading to the observed millimeter spectra is the first step toward a quantitative analysi…

Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics
Jiajie Zhao, Tao Luo, Yaoyu Zhang
https://arxiv.org/abs/2510.09564 https://

Architecture Induces Structural Invariant Manifolds of Neural Network Training Dynamics
While architecture is recognized as key to the performance of deep neural networks, its precise effect on training dynamics has been unclear due to the confounding influence of data and loss functions. This paper proposed an analytic framework based on the geometric control theory to characterize the dynamical properties intrinsic to a model's parameterization. We prove that the Structural Invariant Manifolds (SIMs) of an analytic model $F(\mathbfθ)(\mathbf{x})$--submanifolds that confine grad…

Verifying Graph Neural Networks with Readout is Intractable
Artem Chernobrovkin, Marco S\"alzer, Fran\c{c}ois Schwarzentruber, Nicolas Troquard
https://arxiv.org/abs/2510.08045

Verifying Graph Neural Networks with Readout is Intractable
We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provide a logical characterization and use it to prove that verification tasks for quantized GNNs with readout are (co)NEXPTIME-complete. This result implies that the verification of quantized GNNs is computationally intractable, prompting substantial research efforts toward ensuring the safety of GNN-based systems. We also experimentally demonstrate that quan…

Demystifying the Evolution of Neural Networks with BOM Analysis: Insights from a Large-Scale Study of 55,997 GitHub Repositories
Xiaoning Ren, Yuhang Ye, Xiongfei Wu, Yueming Wu, Yinxing Xue
https://arxiv.org/abs/2509.20010

Demystifying the Evolution of Neural Networks with BOM Analysis: Insights from a Large-Scale Study of 55,997 GitHub Repositories
Neural networks have become integral to many fields due to their exceptional performance. The open-source community has witnessed a rapid influx of neural network (NN) repositories with fast-paced iterations, making it crucial for practitioners to analyze their evolution to guide development and stay ahead of trends. While extensive research has explored traditional software evolution using Software Bill of Materials (SBOMs), these are ill-suited for NN software, which relies on pre-defined mod…

Stacked Regression using Off-the-shelf, Stimulus-tuned and Fine-tuned Neural Networks for Predicting fMRI Brain Responses to Movies (Algonauts 2025 Report)
Robert Scholz, Kunal Bagga, Christine Ahrends, Carlo Alberto Barbano
https://arxiv.org/abs/2510.06235

Stacked Regression using Off-the-shelf, Stimulus-tuned and Fine-tuned Neural Networks for Predicting fMRI Brain Responses to Movies (Algonauts 2025 Report)
We present our submission to the Algonauts 2025 Challenge, where the goal is to predict fMRI brain responses to movie stimuli. Our approach integrates multimodal representations from large language models, video encoders, audio models, and vision-language models, combining both off-the-shelf and fine-tuned variants. To improve performance, we enhanced textual inputs with detailed transcripts and summaries, and we explored stimulus-tuning and fine-tuning strategies for language and vision models…

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks
Shaofei Li, Xiao Han, Ziqi Zhang, Minyao Hua, Shuli Gao, Zhenkai Liang, Yao Guo, Xiangqun Chen, Ding Li
https://arxiv.org/abs/2510.12652

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks
As e-commerce platforms develop, fraudulent activities are increasingly emerging, posing significant threats to the security and stability of these platforms. Promotion abuse is one of the fastest-growing types of fraud in recent years and is characterized by users exploiting promotional activities to gain financial benefits from the platform. To investigate this issue, we conduct the first study on promotion abuse fraud in e-commerce platforms MEITUAN. We find that promotion abuse fraud is a g…

Who Said Neural Networks Aren't Linear?
Nimrod Berman, Assaf Hallak, Assaf Shocher
https://arxiv.org/abs/2510.08570 https://arxiv.org/pdf/2510.08570

Who Said Neural Networks Aren't Linear?
Neural networks are famously nonlinear. However, linearity is defined relative to a pair of vector spaces, $f$$:$$X$$\to$$Y$. Is it possible to identify a pair of non-standard vector spaces for which a conventionally nonlinear function is, in fact, linear? This paper introduces a method that makes such vector spaces explicit by construction. We find that if we sandwich a linear operator $A$ between two invertible neural networks, $f(x)=g_y^{-1}(A g_x(x))$, then the corresponding vector spaces $…

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Xin He, Liangliang You, Hongduan Tian, Bo Han, Ivor Tsang, Yew-Soon Ong
https://arxiv.org/abs/2510.05158

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and error-prone. Scientists must interpret problems as PDE formulations, design architectures and loss functions, and implement stable training pipelines. Existing large language model (LLM) based approaches address isolated steps such as code generation or architecture suggestion, but typically assume a formal PDE is alre…

Learning Polynomial Activation Functions for Deep Neural Networks
Linghao Zhang, Jiawang Nie, Tingting Tang
https://arxiv.org/abs/2510.03682 https://arxiv.…

Learning Polynomial Activation Functions for Deep Neural Networks
Activation functions are crucial for deep neural networks. This novel work frames the problem of training neural network with learnable polynomial activation functions as a polynomial optimization problem, which is solvable by the Moment-SOS hierarchy. This work represents a fundamental departure from the conventional paradigm of training deep neural networks, which relies on local optimization methods like backpropagation and gradient descent. Numerical experiments are presented to demonstrate…

Learning Neuron Dynamics within Deep Spiking Neural Networks
Eric Jahns, Davi Moreno, Michel A. Kinsy
https://arxiv.org/abs/2510.07341 https://arxiv.org/pd…

Learning Neuron Dynamics within Deep Spiking Neural Networks
Spiking Neural Networks (SNNs) offer a promising energy-efficient alternative to Artificial Neural Networks (ANNs) by utilizing sparse and asynchronous processing through discrete spike-based computation. However, the performance of deep SNNs remains limited by their reliance on simple neuron models, such as the Leaky Integrate-and-Fire (LIF) model, which cannot capture rich temporal dynamics. While more expressive neuron models exist, they require careful manual tuning of hyperparameters and a…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Jini Yang, Beomseok Oh, Seungryong Kim, Sunok Kim
https://arxiv.org/abs/2509.22581 https:/…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing…

Diffusion-Guided Renormalization of Neural Systems via Tensor Networks
Nathan X. Kodama
https://arxiv.org/abs/2510.06361 https://arxiv.org/pdf/2510.06361…

Diffusion-Guided Renormalization of Neural Systems via Tensor Networks
Far from equilibrium, neural systems self-organize across multiple scales. Exploiting multiscale self-organization in neuroscience and artificial intelligence requires a computational framework for modeling the effective non-equilibrium dynamics of stochastic neural trajectories. Non-equilibrium thermodynamics and representational geometry offer theoretical foundations, but we need scalable data-driven techniques for modeling collective properties of high-dimensional neural networks from partia…

On the Theory of Continual Learning with Gradient Descent for Neural Networks
Hossein Taheri, Avishek Ghosh, Arya Mazumdar
https://arxiv.org/abs/2510.05573 https://

On the Theory of Continual Learning with Gradient Descent for Neural Networks
Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting the earlier ones, is a central goal of artificial intelligence. To shed light on its underlying mechanisms, we analyze the limitations of continual learning in a tractable yet representative setting. In particular, we study one-hidden-layer quadratic neural networks trained by gradient descent on an XOR cluster dataset with Gaussian noise, where different tasks correspond to different clusters…

Graph Neural Networks in Large Scale Wireless Communication Networks: Scalability Across Random Geometric Graphs
Romina Garcia Camargo, Zhiyang Wang, Alejandro Ribeiro
https://arxiv.org/abs/2510.00896 …

Graph Neural Networks in Large Scale Wireless Communication Networks: Scalability Across Random Geometric Graphs
The growing complexity of wireless systems has accelerated the move from traditional methods to learning-based solutions. Graph Neural Networks (GNNs) are especially well-suited here, since wireless networks can be naturally represented as graphs. A key property of GNNs is transferability: models trained on one graph often generalize to much larger graphs with little performance loss. While empirical studies have shown that GNN-based wireless policies transfer effectively, existing theoretical …

Topological Signatures of ReLU Neural Network Activation Patterns
Vicente Bosca, Tatum Rask, Sunia Tanweer, Andrew R. Tawfeek, Branden Stone
https://arxiv.org/abs/2510.12700 htt…

Topological Signatures of ReLU Neural Network Activation Patterns
This paper explores the topological signatures of ReLU neural network activation patterns. We consider feedforward neural networks with ReLU activation functions and analyze the polytope decomposition of the feature space induced by the network. Mainly, we investigate how the Fiedler partition of the dual graph and show that it appears to correlate with the decision boundary -- in the case of binary classification. Additionally, we compute the homology of the cellular decomposition -- in a regr…

HIV-1 protease cleavage sites detection with a Quantum convolutional neural network algorithm
Junggu Choi, Junho Lee, Kyle L. Jung, Jae U. Jung
https://arxiv.org/abs/2510.01993 …

HIV-1 protease cleavage sites detection with a Quantum convolutional neural network algorithm
In this study, we propose a quantum convolutional neural network (QCNN)-based framework with the neural quantum embedding (NQE) to predict HIV-1 protease cleavage sites in amino acid sequences from viral and human proteins. To assess the effectiveness and robustness of our framework, we compared the classification performance against classical neural networks under both noiseless and noisy simulations. Among experimental conditions, the QCNN with the angle and amplitude encoding NQE conditions …

Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy
Hamidreza Montazeri Hedesh, Milad Siami
https://arxiv.org/abs/2510.06661

Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy
We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verificati…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Xiao Yang, Xuejiao Zhao, Zhiqi Shen
https://arxiv.org/abs/2510.05750 https://…

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Graph neural networks (GNNs) have achieved remarkable success in node classification. Building on this progress, heterogeneous graph neural networks (HGNNs) integrate relation types and node and edge semantics to leverage heterogeneous information. Causal analysis for HGNNs is advancing rapidly, aiming to separate genuine causal effects from spurious correlations. However, whether HGNNs are intrinsically effective remains underexamined, and most studies implicitly assume rather than establish t…

PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks
Nges Brian Njungle, Eric Jahns, Milan Stojkov, Michel A. Kinsy
https://arxiv.org/abs/2510.03995

PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks
Deep learning has become a cornerstone of modern machine learning. It relies heavily on vast datasets and significant computational resources for high performance. This data often contains sensitive information, making privacy a major concern in deep learning. Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional deep learning approaches. Nevertheless, SNNs still depend on large volumes of data, inheriting all the privacy challenges of deep learning. Hom…

Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning
Chenxiang Ma, Xinyi Chen, Yujie Wu, Kay Chen Tan, Jibin Wu
https://arxiv.org/abs/2510.04098 https://

Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning
Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable training overhead, posing challenges for researchers with limited computational resources and hindering the sustained development of SNNs. Data pruning is a promising strategy for accelerating training by retaining the most informative examples and discarding red…

Multi state neurons
Robert Worden
https://arxiv.org/abs/2512.08815 https://arxiv.org/pdf/2512.08815 https://arxiv.org/html/2512.08815
arXiv:2512.08815v1 Announce Type: new
Abstract: Neurons, as eukaryotic cells, have powerful internal computation capabilities. One neuron can have many distinct states, and brains can use this capability. Processes of neuron growth and maintenance use chemical signalling between cell bodies and synapses, ferrying chemical messengers over microtubules and actin fibres within cells. These processes are computations which, while slower than neural electrical signalling, could allow any neuron to change its state over intervals of seconds or minutes. Based on its state, a single neuron can selectively de-activate some of its synapses, sculpting a dynamic neural net from the static neural connections of the brain. Without this dynamic selection, the static neural networks in brains are too amorphous and dilute to do the computations of neural cognitive models. The use of multi-state neurons in animal brains is illustrated in hierarchical Bayesian object recognition. Multi-state neurons may support a design which is more efficient than two-state neurons, and scales better as object complexity increases. Brains could have evolved to use multi-state neurons. Multi-state neurons could be used in artificial neural networks, to use a kind of non-Hebbian learning which is faster and more focused and controllable than traditional neural net learning. This possibility has not yet been explored in computational models.
toXiv_bot_toot

MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition
Ricardo T. Fares, Lucas C. Ribas
https://arxiv.org/abs/2510.03228 https://

MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition
Randomized neural networks for representation learning have consistently achieved prominent results in texture recognition tasks, effectively combining the advantages of both traditional techniques and learning-based approaches. However, existing approaches have so far focused mainly on improving cross-information prediction, without introducing significant advancements to the overall randomized network architecture. In this paper, we propose Mixer, a novel randomized neural network for texture…

Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
Yongqiang Cai, Yifei Duan
https://arxiv.org/abs/2510.03676 https://

Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families
A significant connection exists between the controllability of dynamical systems and the approximation capabilities of neural networks, where residual networks and vanilla feedforward neural networks can both be regarded as numerical discretizations of the flow maps of dynamical systems. Leveraging the expressive power of neural networks, prior works have explored various control families $\mathcal{F}$ that enable the flow maps of dynamical systems to achieve either the universal approximation …

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet
https://arxiv.org/abs/2510.12077

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating…

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima https://arxiv.org/abs/2511.07960 by @… et al.;

Advancing credibility and transparency in brain-to-image reconstruction research: Reanalysis of Koide-Majima, Nishimoto, and Majima (Neural Networks, 2024)
A recent high-profile study by Koide-Majima et al. (2024) claimed a major advance in reconstructing visual imagery from brain activity using a novel variant of a generative AI-based method. However, our independent reanalysis reveals multiple methodological concerns that raise questions about the validity of their conclusions. Specifically, our evaluation demonstrates that: (1) the reconstruction results are biased by selective reporting of only the best-performing examples at multiple levels; …

An in-depth look at approximation via deep and narrow neural networks
Joris Dommel, Sven A. Wegner
https://arxiv.org/abs/2510.07202 https://arxiv.org/pdf/2…

An in-depth look at approximation via deep and narrow neural networks
In 2017, Hanin and Sellke showed that the class of arbitrarily deep, real-valued, feed-forward and ReLU-activated networks of width w forms a dense subset of the space of continuous functions on R^n, with respect to the topology of uniform convergence on compact sets, if and only if w>n holds. To show the necessity, a concrete counterexample function f:R^n->R was used. In this note we actually approximate this very f by neural networks in the two cases w=n and w=n+1 around the aforementioned th…

FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
Nges Brian Njungle, Eric Jahns, Michel A. Kinsy
https://arxiv.org/abs/2510.03996

FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
The widespread adoption of Machine Learning as a Service raises critical privacy and security concerns, particularly about data confidentiality and trust in both cloud providers and the machine learning models. Homomorphic Encryption (HE) has emerged as a promising solution to this problems, allowing computations on encrypted data without decryption. Despite its potential, existing approaches to integrate HE into neural networks are often limited to specific architectures, leaving a wide gap in…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

Stability of Fractional-Order Discrete-Time Systems with Application to Rulkov Neural Networks and Asymmetric Memristor Synapses
Leila Eftekhari, Moein Khalighi, Saeid Abbasbandy
https://arxiv.org/abs/2510.03304

Stability of Fractional-Order Discrete-Time Systems with Application to Rulkov Neural Networks and Asymmetric Memristor Synapses
Memristors have emerged as ideal components for modeling synaptic connections in neural networks due to their ability to emulate synaptic plasticity and memory effects. Discrete models of memristor-coupled neurons are crucial for simplifying computations and efficiently analyzing large-scale neural networks. Furthermore, incorporating fractional-order calculus into discrete models enhances their capacity to capture the memory and hereditary properties inherent in biological neurons, thus reduci…

Bayesian Modelling of Multi-Year Crop Type Classification Using Deep Neural Networks and Hidden Markov Models
Gianmarco Perantoni, Giulio Weikmann, Lorenzo Bruzzone
https://arxiv.org/abs/2510.07008

Bayesian Modelling of Multi-Year Crop Type Classification Using Deep Neural Networks and Hidden Markov Models
The temporal consistency of yearly land-cover maps is of great importance to model the evolution and change of the land cover over the years. In this paper, we focus the attention on a novel approach to classification of yearly satellite image time series (SITS) that combines deep learning with Bayesian modelling, using Hidden Markov Models (HMMs) integrated with Transformer Encoder (TE) based DNNs. The proposed approach aims to capture both i) intricate temporal correlations in yearly SITS and…

Adversarial Attacks Leverage Interference Between Features in Superposition
Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal
https://arxiv.org/abs/2510.11709 https://…

Adversarial Attacks Leverage Interference Between Features in Superposition
Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to non-robust input features. In this paper, we instead argue that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, we show how superposition - where networks represent more features than they have dimensions …

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
Hiroshi Inazawa
https://arxiv.org/abs/2510.06542 https://arxiv.or…

Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
This paper presents a neural network model (associative memory model) for memory and recall of images. In this model, only a single neuron can memorize multi-images and when that neuron is activated, it is possible to recall all the memorized images at the same time. The system is composed of a single cluster of numerous neurons, referred to as the "Cue Ball," and multiple neural network layers, collectively called the "Recall Net." One of the features of this model is that several different im…

Spiking Neural Networks: a theoretical framework for Universal Approximation and training
Umberto Biccari
https://arxiv.org/abs/2509.21920 https://arxiv.or…

Spiking Neural Networks: a theoretical framework for Universal Approximation and training
Spiking Neural Networks (SNNs) are widely regarded as a biologically-inspired and energy-efficient alternative to classical artificial neural networks. Yet, their theoretical foundations remain only partially understood. In this work, we develop a rigorous mathematical analysis of a representative SNN architecture based on Leaky Integrate-and-Fire (LIF) neurons with threshold-reset dynamics. Our contributions are twofold. First, we establish a universal approximation theorem showing that SNNs c…

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networks
Alejandro Almod\'ovar, Patricia A. Apell\'aniz, Santiago Zazo, Juan Parras
https://arxiv.org/abs/2509.22467

CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networks
Deep neural networks achieve state-of-the-art performance in estimating heterogeneous treatment effects, but their opacity limits trust and adoption in sensitive domains such as medicine, economics, and public policy. Building on well-established and high-performing causal neural architectures, we propose causalKANs, a framework that transforms neural estimators of conditional average treatment effects (CATEs) into Kolmogorov--Arnold Networks (KANs). By incorporating pruning and symbolic simpli…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

macaque_neural: Macaque cortical connectivity (Young)
A network of cortical regions in the Macaque cortex.
This network has 47 nodes and 505 edges.
Tags: Biological, Connectome, Unweighted
https://networks.skewed.de/net/macaque_neural
Ridiculogram:

Non-linear associations of amyloid-$\beta$ with resting-state functional networks and their cognitive relevance in a large community-based cohort of cognitively normal older adults
Junjie Wu, Benjamin B Risk, Taylor A James, Nicholas Seyfried, David W Loring, Felicia C Goldstein, Allan I Levey, James J Lah, Deqiang Qiu
https://arxiv.org/ab…

Non-linear associations of amyloid-$β$ with resting-state functional networks and their cognitive relevance in a large community-based cohort of cognitively normal older adults
Background: Non-linear alterations in brain network connectivity may represent early neural signatures of Alzheimer's disease (AD) pathology in cognitively normal older adults. Understanding these changes and their cognitive relevance could provide sensitive biomarkers for early detection. Most prior studies recruited participants from memory clinics, often with subjective memory concerns, limiting generalizability. Methods: We examined 14 large-scale functional brain networks in 968 cognitiv…

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
Birk Torpmann-Hagen, Michael A. Riegler, P{\aa}l Halvorsen, Dag Johansen
https://arxiv.org/abs/2509.20399

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
Deep neural networks are being utilized in a growing number of applications, both in production systems and for personal use. Network checkpoints are as a consequence often shared and distributed on various platforms to ease the development process. This work considers the threat of neural network stegomalware, where malware is embedded in neural network checkpoints at a negligible cost to network accuracy. This constitutes a significant security concern, but is nevertheless largely neglected b…

ERDE: Entropy-Regularized Distillation for Early-exit
Martial Guidez, Stefan Duffner, Yannick Alpou, Oscar R\"oth, Christophe Garcia
https://arxiv.org/abs/2510.04856 https:…

ERDE: Entropy-Regularized Distillation for Early-exit
Although deep neural networks and in particular Convolutional Neural Networks have demonstrated state-of-the-art performance in image classification with relatively high efficiency, they still exhibit high computational costs, often rendering them impractical for real-time and edge applications. Therefore, a multitude of compression techniques have been developed to reduce these costs while maintaining accuracy. In addition, dynamic architectures have been introduced to modulate the level of co…

Random Feature Spiking Neural Networks
Maximilian Gollwitzer, Felix Dietrich
https://arxiv.org/abs/2510.01012 https://arxiv.org/pdf/2510.01012

Random Feature Spiking Neural Networks
Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity of the spiking mechanism can make these models very difficult to train with algorithms based on propagating gradients through the spiking non-linearity. We address this problem by adapting the paradigm of Random Feature Methods (RFMs) from Artificial Neural Ne…

Quantitative convergence of trained single layer neural networks to Gaussian processes
Eloy Mosig, Andrea Agazzi, Dario Trevisan
https://arxiv.org/abs/2509.24544 https://…

Quantitative convergence of trained single layer neural networks to Gaussian processes
In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence under broad settings, precise, finite-width estimates remain limited, particularly during training. We provide explicit upper bounds on the quadratic Wasserstein distance between the network output and its Gaussian approximation at any training time $t \ge 0…

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural
Rid…

QGraphLIME - Explaining Quantum Graph Neural Networks
Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
https://arxiv.org/abs/2510.05683 https://arxi…

QGraphLIME - Explaining Quantum Graph Neural Networks
Quantum graph neural networks offer a powerful paradigm for learning on graph-structured data, yet their explainability is complicated by measurement-induced stochasticity and the combinatorial nature of graph structure. In this paper, we introduce QuantumGraphLIME (QGraphLIME), a model-agnostic, post-hoc framework that treats model explanations as distributions over local surrogates fit on structure-preserving perturbations of a graph. By aggregating surrogate attributions together with their …

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
Firas Ben Hmida, Abderrahmen Amich, Ata Kaboudi, Birhanu Eshete
https://arxiv.org/abs/2509.26562

DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
Deep neural networks (DNNs) are increasingly being deployed in high-stakes applications, from self-driving cars to biometric authentication. However, their unpredictable and unreliable behaviors in real-world settings require new approaches to characterize and ensure their reliability. This paper introduces DeepProv, a novel and customizable system designed to capture and characterize the runtime behavior of DNNs during inference by using their underlying graph structure. Inspired by system a…

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
Irene Tenison, Soumyajit Chatterjee, Fahim Kawsar, Mohammad Malekzadeh
https://arxiv.org/abs/2510.03101

AdaBet: Gradient-free Layer Selection for Efficient Training of Deep Neural Networks
To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a target dataset can facilitate such adaptations; however, it remains impractical due to the increasing depth of modern neural nets, as well as the computational overhead associated with gradient-based optimization across all layers. Current approaches reduce trai…

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural
Rid…

FACE: Faithful Automatic Concept Extraction
Dipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi
https://arxiv.org/abs/2510.11675 https://arxiv.…

FACE: Faithful Automatic Concept Extraction
Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with…

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
Yang Cao, Zhao Song, Jiahao Zhang, Jiale Zhao
https://arxiv.org/abs/2510.05494

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
Graph neural networks (GNNs) have become a core paradigm for learning on relational data. In materials science, equivariant GNNs (EGNNs) have emerged as a compelling backbone for crystalline-structure prediction, owing to their ability to respect Euclidean symmetries and periodic boundary conditions. Despite strong empirical performance, their expressive power in periodic, symmetry-constrained settings remains poorly understood. This work characterizes the intrinsic computational and expressive…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Yankun Han
https://arxiv.org/abs/2510.09423 https://arxiv.org…

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models
Weight initialization governs signal propagation and gradient flow at the start of training. This paper offers a theory-grounded and empirically validated study across two regimes: compact ReLU multilayer perceptrons and GPT-2-style transformers. First, a logarithmic sweep of the initial standard deviation maps vanishing and exploding regimes and identifies a broad stability band with standard deviations between 1e-2 and 1e-1. Second, a controlled comparison shows that Kaiming (fan-in) initiali…

Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
https://arxiv.org/abs/2510.06066

Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
In this paper, we study the factors that contribute to the effect of oversmoothing in deep Graph Neural Networks (GNNs). Specifically, our analysis is based on a new metric (Mean Average Squared Distance - $MASED$) to quantify the extent of oversmoothing. We derive layer-wise bounds on $MASED$, which aggregate to yield global upper and lower distance bounds. Based on this quantification of oversmoothing, we further analyze the importance of two different properties of the model; namely the norm…

celegansneural: C. elegans neurons (1986)
A network representing the neural connections of the Caenorhabditis elegans nematode.
This network has 297 nodes and 2359 edges.
Tags: Biological, Connectome, Weighted
https://networks.skewed.de/net/celegansneural
Rid…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- The Diffusion Duality
Sahoo, Deschenaux, Gokaslan, Wang, Chiu, Kuleshov
https://arxiv.org/abs/2506.10892 https://mastoxiv.page/@arXiv_csLG_bot/114675526577078472
- Multimodal Representation Learning and Fusion
Jin, Ge, Xie, Luo, Song, Bi, Liang, Guan, Yeong, Song, Hao
https://arxiv.org/abs/2506.20494 https://mastoxiv.page/@arXiv_csLG_bot/114749113025183688
- The kernel of graph indices for vector search
Mariano Tepper, Ted Willke
https://arxiv.org/abs/2506.20584 https://mastoxiv.page/@arXiv_csLG_bot/114749118923266356
- OptScale: Probabilistic Optimality for Inference-time Scaling
Youkang Wang, Jian Wang, Rubing Chen, Xiao-Yong Wei
https://arxiv.org/abs/2506.22376 https://mastoxiv.page/@arXiv_csLG_bot/114771735361664528
- Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods
Fabian Akkerman, Julien Ferry, Christian Artigues, Emmanuel Hebrard, Thibaut Vidal
https://arxiv.org/abs/2507.18242 https://mastoxiv.page/@arXiv_csLG_bot/114913322736512937
- MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
Runwen Hu, Peilin Chen, Keyan Ding, Shiqi Wang
https://arxiv.org/abs/2508.17702 https://mastoxiv.page/@arXiv_csLG_bot/115095014405732247
- Dual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Protot...
Fatema Siddika, Md Anwar Hossen, Wensheng Zhang, Anuj Sharma, Juan Pablo Mu\~noz, Ali Jannesari
https://arxiv.org/abs/2508.19009 https://mastoxiv.page/@arXiv_csLG_bot/115100269482762688
- STDiff: A State Transition Diffusion Framework for Time Series Imputation in Industrial Systems
Gary Simethy, Daniel Ortiz-Arroyo, Petar Durdevic
https://arxiv.org/abs/2508.19011 https://mastoxiv.page/@arXiv_csLG_bot/115100270137397046
- EEGDM: Learning EEG Representation with Latent Diffusion Model
Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu
https://arxiv.org/abs/2508.20705 https://mastoxiv.page/@arXiv_csLG_bot/115111565155687451
- Data-Free Continual Learning of Server Models in Model-Heterogeneous Cloud-Device Collaboration
Xiao Zhang, Zengzhe Chen, Yuan Yuan, Yifei Zou, Fuzhen Zhuang, Wenyu Jiao, Yuke Wang, Dongxiao Yu
https://arxiv.org/abs/2509.25977 https://mastoxiv.page/@arXiv_csLG_bot/115298721327100391
- Fine-Tuning Masked Diffusion for Provable Self-Correction
Jaeyeon Kim, Seunggeun Kim, Taekyun Lee, David Z. Pan, Hyeji Kim, Sham Kakade, Sitan Chen
https://arxiv.org/abs/2510.01384 https://mastoxiv.page/@arXiv_csLG_bot/115309690976554356
- A Generic Machine Learning Framework for Radio Frequency Fingerprinting
Alex Hiles, Bashar I. Ahmad
https://arxiv.org/abs/2510.09775 https://mastoxiv.page/@arXiv_csLG_bot/115372387779061015
- ASecond-Order SpikingSSM for Wearables
Kartikay Agrawal, Abhijeet Vikram, Vedant Sharma, Vaishnavi Nagabhushana, Ayon Borthakur
https://arxiv.org/abs/2510.14386 https://mastoxiv.page/@arXiv_csLG_bot/115389079527543821
- Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
Heming Zou, Yixiu Mao, Yun Qu, Qi Wang, Xiangyang Ji
https://arxiv.org/abs/2510.16882 https://mastoxiv.page/@arXiv_csLG_bot/115412243355962887
- Seeing Structural Failure Before it Happens: An Image-Based Physics-Informed Neural Network (PINN...
Omer Jauhar Khan, Sudais Khan, Hafeez Anwar, Shahzeb Khan, Shams Ul Arifeen
https://arxiv.org/abs/2510.23117 https://mastoxiv.page/@arXiv_csLG_bot/115451891042176876
- Training Deep Physics-Informed Kolmogorov-Arnold Networks
Spyros Rigas, Fotios Anagnostopoulos, Michalis Papachristou, Georgios Alexandridis
https://arxiv.org/abs/2510.23501 https://mastoxiv.page/@arXiv_csLG_bot/115451942159737549
- Semi-Supervised Preference Optimization with Limited Feedback
Seonggyun Lee, Sungjun Lim, Seojin Park, Soeun Cheon, Kyungwoo Song
https://arxiv.org/abs/2511.00040 https://mastoxiv.page/@arXiv_csLG_bot/115490555013124989
- Towards Causal Market Simulators
Dennis Thumm, Luis Ontaneda Mijares
https://arxiv.org/abs/2511.04469 https://mastoxiv.page/@arXiv_csLG_bot/115507943827841017
- Incremental Generation is Necessary and Sufficient for Universality in Flow-Based Modelling
Hossein Rouhvarzi, Anastasis Kratsios
https://arxiv.org/abs/2511.09902 https://mastoxiv.page/@arXiv_csLG_bot/115547587245365920
- Optimizing Mixture of Block Attention
Guangxuan Xiao, Junxian Guo, Kasra Mazaheri, Song Han
https://arxiv.org/abs/2511.11571 https://mastoxiv.page/@arXiv_csLG_bot/115564541392410174
- Assessing Automated Fact-Checking for Medical LLM Responses with Knowledge Graphs
Shasha Zhou, Mingyu Huang, Jack Cole, Charles Britton, Ming Yin, Jan Wolber, Ke Li
https://arxiv.org/abs/2511.12817 https://mastoxiv.page/@arXiv_csLG_bot/115570877730326947
toXiv_bot_toot

Adaptive Node Feature Selection For Graph Neural Networks
Ali Azizpour, Madeline Navarro, Santiago Segarra
https://arxiv.org/abs/2510.03096 https://arxiv.o…

Adaptive Node Feature Selection For Graph Neural Networks
We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training. The ability to measure how features contribute to model output is key for interpreting decisions, reducing dimensionality, and even improving performance by eliminating unhelpful variables. However, graph-structured data introduces complex dependencies that may not be amenable to classical feature importance metrics. Inspired by this challenge…

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
Leonardo Defilippis, Yizhou Xu, Julius Girardin, Emanuele Troiani, Vittorio Erba, Lenka Zdeborov\'a, Bruno Loureiro, Florent Krzakala
https://arxiv.org/abs/2509.24882

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
Neural scaling laws underlie many of the recent advances in deep learning, yet their theoretical understanding remains largely confined to linear models. In this work, we present a systematic analysis of scaling laws for quadratic and diagonal neural networks in the feature learning regime. Leveraging connections with matrix compressed sensing and LASSO, we derive a detailed phase diagram for the scaling exponents of the excess risk as a function of sample complexity and weight decay. This anal…

Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
Vu Duc Anh Nguyen, Ziyue Li
https://arxiv.org/abs/2510.09350 https://…

Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
The operational efficiency of railway networks, a cornerstone of modern economies, is persistently undermined by the cascading effects of train delays. Accurately forecasting this delay propagation is a critical challenge for real-time traffic management. While recent research has leveraged Graph Neural Networks (GNNs) to model the network structure of railways, a significant gap remains in developing frameworks that provide multi-step autoregressive forecasts at a network-wide scale, while sim…

Towards generalizable deep ptychography neural networks
Albert Vong, Steven Henke, Oliver Hoidn, Hanna Ruth, Junjing Deng, Alexander Hexemer, Apurva Mehta, Arianna Gleason, Levi Hancock, Nicholas Schwarz
https://arxiv.org/abs/2509.25104

Towards generalizable deep ptychography neural networks
X-ray ptychography is a data-intensive imaging technique expected to become ubiquitous at next-generation light sources delivering many-fold increases in coherent flux. The need for real-time feedback under accelerated acquisition rates motivates surrogate reconstruction models like deep neural networks, which offer orders-of-magnitude speedup over conventional methods. However, existing deep learning approaches lack robustness across diverse experimental conditions. We propose an unsupervised …

A Recovery Guarantee for Sparse Neural Networks
Sara Fridovich-Keil, Mert Pilanci
https://arxiv.org/abs/2509.20323 https://arxiv.org/pdf/2509.20323

A Recovery Guarantee for Sparse Neural Networks
We prove the first guarantees of sparse recovery for ReLU neural networks, where the sparse network weights constitute the signal to be recovered. Specifically, we study structural properties of the sparse network weights for two-layer, scalar-output networks under which a simple iterative hard thresholding algorithm recovers these weights exactly, using memory that grows linearly in the number of nonzero weights. We validate this theoretical result with simple experiments on recovery of sparse…

Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
Kevin Raina, Tanya Schmah
https://arxiv.org/abs/2510.06025 https://

Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
Out-of-Distribution (OOD) detection is critical to AI reliability and safety, yet in many practical settings, only a limited amount of training data is available. Bayesian Neural Networks (BNNs) are a promising class of model on which to base OOD detection, because they explicitly represent epistemic (i.e. model) uncertainty. In the small training data regime, BNNs are especially valuable because they can incorporate prior model information. We introduce a new family of Bayesian posthoc OOD sco…

Neural Feature Geometry Evolves as Discrete Ricci Flow
Moritz Hehl, Max von Renesse, Melanie Weber
https://arxiv.org/abs/2509.22362 https://arxiv.org/pdf/2…

Neural Feature Geometry Evolves as Discrete Ricci Flow
Deep neural networks learn feature representations via complex geometric transformations of the input data manifold. Despite the models' empirical success across domains, our understanding of neural feature representations is still incomplete. In this work we investigate neural feature geometry through the lens of discrete geometry. Since the input data manifold is typically unobserved, we approximate it using geometric graphs that encode local similarity structure. We provide theoretical resul…

BrainIB : Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
Tianzheng Hu, Qiang Li, Shu Liu, Vince D. Calhoun, Guido van Wingen, Shujian Yu
https://arxiv.org/abs/2510.03004

BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been developed to identify brain biomarkers that differentiate psychiatric disorders from healthy controls. However, conventional machine learning-based diagnostic models often depend on extensive feature engineering, which introduces bias through manual intervention. While deep learning…

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Arindam Chowdhury, Massimiliano Lupo Pasini
https://arxiv.org/abs/2510.05583 https://

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable the modeling of complex physics. While most recent GNNs combine more traditional message passing neural networks (MPNNs) layers to model short-range interactions with more advanced graph transformers (GTs) with global attention mechanisms to model long-range …

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Alessandro Favero
https://arxiv.org/abs/2510.06106 https://arxiv.…

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally statistically intractable due to the curse of dimensionality. This apparent paradox suggests that learnable data must have an underlying latent structure. What is the nature of this structure? How do neural networks encode and exploit it, and how does it quantitatively impact performance - for instance, how does general…

Fine-Grained Urban Traffic Forecasting on Metropolis-Scale Road Networks
Fedor Velikonivtsev, Oleg Platonov, Gleb Bazhenov, Liudmila Prokhorenkova
https://arxiv.org/abs/2510.02278

Fine-Grained Urban Traffic Forecasting on Metropolis-Scale Road Networks
Traffic forecasting on road networks is a complex task of significant practical importance that has recently attracted considerable attention from the machine learning community, with spatiotemporal graph neural networks (GNNs) becoming the most popular approach. The proper evaluation of traffic forecasting methods requires realistic datasets, but current publicly available benchmarks have significant drawbacks, including the absence of information about road connectivity for road graph constru…

KoALA: KL-L0 Adversarial Detector via Label Agreement
Siqi Li, Yasser Shoukry
https://arxiv.org/abs/2510.12752 https://arxiv.org/pdf/2510.12752

KoALA: KL-L0 Adversarial Detector via Label Agreement
Deep neural networks are highly susceptible to adversarial attacks, which pose significant risks to security- and safety-critical applications. We present KoALA (KL-L0 Adversarial detection via Label Agreement), a novel, semantics-free adversarial detector that requires no architectural changes or adversarial retraining. KoALA operates on a simple principle: it detects an adversarial attack when class predictions from two complementary similarity metrics disagree. These metrics-KL divergence an…

Physics-Informed Machine Learning in Biomedical Science and Engineering
Nazanin Ahmadi, Qianying Cao, Jay D. Humphrey, George Em Karniadakis
https://arxiv.org/abs/2510.05433 htt…

Physics-Informed Machine Learning in Biomedical Science and Engineering
Physics-informed machine learning (PIML) is emerging as a potentially transformative paradigm for modeling complex biomedical systems by integrating parameterized physical laws with data-driven methods. Here, we review three main classes of PIML frameworks: physics-informed neural networks (PINNs), neural ordinary differential equations (NODEs), and neural operators (NOs), highlighting their growing role in biomedical science and engineering. We begin with PINNs, which embed governing equations…

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
Yehonatan Refael, Guy Smorodinsky, Ofir Lindenbaum, Itay Safran
https://arxiv.org/abs/2509.21296

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters. Some of these methods exploit implicit bias toward margin maximization, suggesting that properties often regarded as beneficial for generalization may actually compromise privacy. Yet despite striking empirical demonstrations, the reliability of these attacks…

Superposition disentanglement of neural representations reveals hidden alignment
Andr\'e Longon, David Klindt, Meenakshi Khosla
https://arxiv.org/abs/2510.03186 https://

Superposition disentanglement of neural representations reveals hidden alignment
The superposition hypothesis states that a single neuron within a population may participate in the representation of multiple features in order for the population to represent more features than the number of neurons. In neuroscience and AI, representational alignment metrics measure the extent to which different deep neural networks (DNNs) or brains represent similar information. In this work, we explore a critical question: \textit{does superposition interact with alignment metrics in any un…