Tootfinder

We shape our X and then our X shape us.
vs
Our X shape us and then we shape our X.
(Where X ∊ { biases, beliefs, connections, data, emotions, environments, experiences, fears, languages, music, nature, networks, time, tools... })

ResQ: A Novel Framework to Implement Residual Neural Networks on Analog Rydberg Atom Quantum Computers
Nicholas S. DiBrita, Jason Han, Tirthak Patel
https://arxiv.org/abs/2506.21537

ResQ: A Novel Framework to Implement Residual Neural Networks on Analog Rydberg Atom Quantum Computers
Research in quantum machine learning has recently proliferated due to the potential of quantum computing to accelerate machine learning. An area of machine learning that has not yet been explored is neural ordinary differential equation (neural ODE) based residual neural networks (ResNets), which aim to improve the effectiveness of neural networks using the principles of ordinary differential equations. In this work, we present our insights about why analog Rydberg atom quantum computers are es…

Spiking Neural Networks for SAR Interferometric Phase Unwrapping: A Theoretical Framework for Energy-Efficient Processing
Marc Bara
https://arxiv.org/abs/2506.20782

Spiking Neural Networks for SAR Interferometric Phase Unwrapping: A Theoretical Framework for Energy-Efficient Processing
We present the first theoretical framework for applying spiking neural networks (SNNs) to synthetic aperture radar (SAR) interferometric phase unwrapping. Despite extensive research in both domains, our comprehensive literature review confirms that SNNs have never been applied to phase unwrapping, representing a significant gap in current methodologies. As Earth observation data volumes continue to grow exponentially (with missions like NISAR expected to generate 100PB in two years) energy-effi…

Evolution and determinants of firm-level systemic risk in local production networks
Anna Mancini, Bal\'azs Lengyel, Riccardo Di Clemente, Giulio Cimini
https://arxiv.org/abs/2506.21426

Evolution and determinants of firm-level systemic risk in local production networks
Recent crises like the COVID-19 pandemic and geopolitical tensions have exposed vulnerabilities and caused disruptions of supply chains, leading to product shortages, increased costs, and economic instability. This has prompted increasing efforts to assess systemic risk, namely the effects of firm disruptions on entire economies. However, the ability of firms to react to crises by rewiring their supply links has been largely overlooked, limiting our understanding of production networks resilien…

Real-time and personalized product recommendations for large e-commerce platforms
Matteo Tolloso, Davide Bacciu, Shahab Mokarizadeh, Marco Varesi
https://arxiv.org/abs/2506.21368 …

Real-time and personalized product recommendations for large e-commerce platforms
We present a methodology to provide real-time and personalized product recommendations for large e-commerce platforms, specifically focusing on fashion retail. Our approach aims to achieve accurate and scalable recommendations with minimal response times, ensuring user satisfaction, leveraging Graph Neural Networks and parsimonious learning methodologies. Extensive experimentation with datasets from one of the largest e-commerce platforms demonstrates the effectiveness of our approach in foreca…

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
Kyeongwon Lee, Lizhen Lin, Jaewoo Park, Seonghyun Jeong
https://arxiv.org/abs/2506.19144

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
This work establishes that sparse Bayesian neural networks achieve optimal posterior contraction rates over anisotropic Besov spaces and their hierarchical compositions. These structures reflect the intrinsic dimensionality of the underlying function, thereby mitigating the curse of dimensionality. Our analysis shows that Bayesian neural networks equipped with either sparse or continuous shrinkage priors attain the optimal rates which are dependent on the intrinsic dimension of the true structu…

Identifiability and Maximum Likelihood Estimation for System Identification of Networks of Dynamical Systems
Anders Hansson, Jo\~ao Victor Galv\~ao da Mata, Martin S. Andersen
https://arxiv.org/abs/2506.20628

Identifiability and Maximum Likelihood Estimation for System Identification of Networks of Dynamical Systems
In this paper we investigate identifiability and maximum likelihood estimation for direct system identification of networks of dynamical systems. We provide necessary and sufficient conditions for network identifiability in terms of Gröbner bases. We show that the maximum likelihood approach is both consistent and efficient, which is in contrast to existing prediction error approaches. Moreover, our approach has wider applicability, i.e., it is applicable whenever network identifiability holds…

This https://arxiv.org/abs/2505.03458 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

The classification of Alzheimer's disease and mild cognitive impairment improved by dynamic functional network analysis
Brain network analysis using functional MRI has advanced our understanding of cortical activity and its changes in neurodegenerative disorders that cause dementia. Recently, research in brain connectivity has focused on dynamic (time-varying) brain networks that capture both spatial and temporal information on cortical, regional co-activity patterns. However, this approach has been largely unexplored within the Alzheimer's spectrum. We analysed age- and sex-matched static and dynamic fMRI brain…

E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs
Van-Hoang Phan, Long-Khanh Pham, Dang Vu, Anh-Duy Tran, Minh-Son Dao
https://arxiv.org/abs/2506.20944

E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs
The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessment. By dynamically retrieving and cross-referencing trusted data sources, our approach mitigates vulnerabilities of traditional training-based models, such as adversarial attacks and data poisoning. Addi…

General theory of perturbation of infinite resistor networks
J\'ozsef Cserti, Gyula D\'avid
https://arxiv.org/abs/2506.18654 https://

General theory of perturbation of infinite resistor networks
The effective resistance between any two nodes in a perturbed resistor network is determined by removing multiple bonds from an infinite resistor lattice. We have developed an efficient method for calculating the Green operator of the Laplacian for such perturbed networks, which is directly related to the two-point resistance. Unlike the recursive techniques that remove bonds one at a time, our approach handles all bond modifications simultaneously. To demonstrate the versatility of our m…

Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks
Masudul Hasan Masud Bhuiyan, Gianluca De Stefano, Giancarlo Pellegrino, Cristian-Alexandru Staicu
https://arxiv.org/abs/2506.18191

Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks
Static analysis plays a key role in finding bugs, including security issues. A critical step in static analysis is building accurate call graphs that model function calls in a program. However, due to hard-to-analyze language features, existing call graph construction algorithms for JavaScript are neither sound nor complete. Prior work shows that even advanced solutions produce false edges and miss valid ones. In this work, we assist these tools by identifying missed call edges. Our main idea i…

Practical insights on the effect of different encodings, ans\"atze and measurements in quantum and hybrid convolutional neural networks
Jes\'us Lozano-Cruz, Albert Nieto-Morales, Oriol Ball\'o-Gimbernat, Adan Garriga, Ant\'on Rodr\'iguez-Otero, Alejandro Borrallo-Rentero
https://arxiv.org/abs/2506.20355

Practical insights on the effect of different encodings, ansätze and measurements in quantum and hybrid convolutional neural networks
This study investigates the design choices of parameterized quantum circuits (PQCs) within quantum and hybrid convolutional neural network (HQNN and QCNN) architectures, applied to the task of satellite image classification using the EuroSAT dataset. We systematically evaluate the performance implications of data encoding techniques, variational ansätze, and measurement in approx. 500 distinct model configurations. Our analysis reveals a clear hierarchy of influence on model performance. For h…

DPG loss functions for learning parameter-to-solution maps by neural networks
Pablo Cort\'es Castillo, Wolfgang Dahmen, Jay Gopalakrishnan
https://arxiv.org/abs/2506.18773

DPG loss functions for learning parameter-to-solution maps by neural networks
We develop, analyze, and experimentally explore residual-based loss functions for machine learning of parameter-to-solution maps in the context of parameter-dependent families of partial differential equations (PDEs). Our primary concern is on rigorous accuracy certification to enhance prediction capability of resulting deep neural network reduced models. This is achieved by the use of variationally correct loss functions. Through one specific example of an elliptic PDE, details for establishin…

Jet Reconstruction with Mamba Networks in Collider Events
Jinmian Li, Peng Li, Bingwei Long, Rao Zhang
https://arxiv.org/abs/2506.18336 https://

Jet Reconstruction with Mamba Networks in Collider Events
We introduce a novel end-to-end framework for jet reconstruction in high-energy collider events, leveraging the efficiency and long-range modeling capabilities of the Mamba architecture. Our model unifies instance segmentation, classification, and kinematic regression into a single multi-task learning system, enabling a sophisticated multi-level reconstruction that simultaneously identifies primary heavy jets ($t$, $H$, $W/Z$) and their constituent sub-jets. To facilitate supervised learning fo…

Cascade-driven opinion dynamics on social networks
Elisabetta Biondi, Chiara Boldrini, Andrea Passarella, Marco Conti
https://arxiv.org/abs/2506.16302 http…

Cascade-driven opinion dynamics on social networks
Online social networks (OSNs) have transformed the way individuals fulfill their social needs and consume information. As OSNs become increasingly prominent sources for news dissemination, individuals often encounter content that influences their opinions through both direct interactions and broader network dynamics. In this paper, we propose the Friedkin-Johnsen on Cascade (FJC) model, which is, to the best of our knowledge, is the first attempt to integrate information cascades and opinion dy…

Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks
Samer Lahoud, Kinda Khawam
https://arxiv.org/abs/2506.17063

Client Selection Strategies for Federated Semantic Communications in Heterogeneous IoT Networks
The exponential growth of IoT devices presents critical challenges in bandwidth-constrained wireless networks, particularly regarding efficient data transmission and privacy preservation. This paper presents a novel federated semantic communication (SC) framework that enables collaborative training of bandwidth-efficient models for image reconstruction across heterogeneous IoT devices. By leveraging SC principles to transmit only semantic features, our approach dramatically reduces communicatio…

Noise-tolerant tomography of multimode linear optical interferometers with single photons
Yu. A. Biriukov, R. D. Morozov, I. V. Dyakonov, M. V. Rakhlin, A. I. Galimov, G. V. Klimko, S. V. Sorokin, I. V. Sedova, M. M. Kulagina, Yu. M. Zadiranov, A. A. Toropov, A. A. Korneev, S. P. Kulik, S. S. Straupe
https://arxiv.org/abs/2506.2…

Noise-tolerant tomography of multimode linear optical interferometers with single photons
Linear optical networks are fundamental to the advancement of quantum technologies, including quantum computing, communication, and sensing. The accurate characterization of these networks, described by unitary matrices, is crucial to their effective utilization and scalability. In this work, we present the method for reconstructing the transfer matrix of a linear optical interferometer based on the analysis of cross-correlation functions of photon counts between pairs of output modes. Our appr…

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Mahin Montasir Afif, Abdullah Al Noman, K. M. Tahsin Kabir, Md. Mortuza Ahmmed, Md. Mostafizur Rahman, Mufti Mahmud, Md. Ashraful Babu
https://arxiv.org/abs/2506.17165

Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
Generative Adversarial Networks (GAN) have shown potential in expanding limited medical imaging datasets. This study explores how different ratios of GAN-generated and real brain tumor MRI images impact the performance of a CNN in classifying healthy vs. tumorous scans. A DCGAN was used to create synthetic images which were mixed with real ones at various ratios to train a custom CNN. The CNN was then evaluated on a separate real-world test set. Our results indicate that the model maintains hig…

Finite-Time Information-Theoretic Bounds in Queueing Control
Yujie Liu, Vincent Y. F. Tan, Yunbei Xu
https://arxiv.org/abs/2506.18278 https://

Finite-Time Information-Theoretic Bounds in Queueing Control
We establish the first finite-time information-theoretic lower bounds-and derive new policies that achieve them-for the total queue length in scheduling problems over stochastic processing networks with both adversarial and stochastic arrivals. Prior analyses of MaxWeight guarantee only stability and asymptotic optimality in heavy traffic; we prove that, at finite horizons, MaxWeight can incur strictly larger backlog by problem-dependent factors which we identify. Our main innovations are 1) a …

Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
M. Janssen, C. -k. Chan, J. Davelaar, M. Wielgus
https://arxiv.org/abs/2506.13875

Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
(abridged) In this second paper in our publication series, we present the open-source Zingularity framework for parameter inference with deep Bayesian artificial neural networks. We carried out out supervised learning with synthetic millimeter very long baseline interferometry observations of the EHT. Our ground-truth models are based on GRMHD simulations of Sgr A* and M87* on horizon scales. We investigated how well Zingularity neural networks are able to infer key model parameters from EHT ob…

EPBench: A Benchmark for Short-term Earthquake Prediction with Neural Networks
Zhiyu Xu, Qingliang Chen
https://arxiv.org/abs/2505.15588 https://

EPBench: A Benchmark for Short-term Earthquake Prediction with Neural Networks
Since the beginning of this century, the significant advancements in artificial intelligence and neural networks have offered the potential to bring new transformations to short-term earthquake prediction research. However, currently, there is no widely used benchmark for this task. To address this, we have built a new benchmark (EPBench), which is, to our knowledge, the first global regional-scale short-term earthquake prediction benchmark. Our benchmark comprises 924,472 earthquake records an…

Metacurity is pleased to offer our free and premium subscribers a weekly digest of the best long-form (and longish) infosec-related pieces we couldn't properly fit into our daily news crush.
This week's selection covers
--Bashar al-Assad was toppled by spyware,
--Facial recognition threatens us all with deportation,
--VC money fuels worker surveillance,
--Will Trump launch offensive cyber ops on US networks?,
--The Pall Mall Process and commercial c…

Best infosec-related long reads for the week of 5/31/25
Bashar al-Assad was toppled by spyware, Facial recognition threatens us all with deportation, VC money fuels worker surveillance, Will Trump launch offensive cyber ops on US networks?, The Pall Mall Process and commercial cyber intrusions, Self-confidence leads to GenAI skepticism, more

Robust PDE discovery under sparse and highly noisy conditions via attention neural networks
Shilin Zhang, Yunqing Huang, Nianyu Yi, shihan Zhang
https://arxiv.org/abs/2506.17908

Robust PDE discovery under sparse and highly noisy conditions via attention neural networks
The discovery of partial differential equations (PDEs) from experimental data holds great promise for uncovering predictive models of complex physical systems. In this study, we introduce an efficient automatic model discovery framework, ANN-PYSR, which integrates attention neural networks with the state-of-the-art PySR symbolic regression library. Our approach successfully identifies the governing PDE in six benchmark examples. Compared to the DLGA framework, numerical experiments demonstrate …

Making deep neural networks work for medical audio: representation, compression and domain adaptation
Charles C Onu
https://arxiv.org/abs/2506.13970 https:…

Making deep neural networks work for medical audio: representation, compression and domain adaptation
This thesis addresses the technical challenges of applying machine learning to understand and interpret medical audio signals. The sounds of our lungs, heart, and voice convey vital information about our health. Yet, in contemporary medicine, these sounds are primarily analyzed through auditory interpretation by experts using devices like stethoscopes. Automated analysis offers the potential to standardize the processing of medical sounds, enable screening in low-resource settings where physici…

Lookup Table-based Multiplication-free All-digital DNN Accelerator Featuring Self-Synchronous Pipeline Accumulation
Hiroto Tagata, Takashi Sato, Hiromitsu Awano
https://arxiv.org/abs/2506.16800

Lookup Table-based Multiplication-free All-digital DNN Accelerator Featuring Self-Synchronous Pipeline Accumulation
Deep neural networks (DNNs) have been widely applied in our society, yet reducing power consumption due to large-scale matrix computations remains a critical challenge. MADDNESS is a known approach to improving energy efficiency by substituting matrix multiplication with table lookup operations. Previous research has employed large analog computing circuits to convert inputs into LUT addresses, which presents challenges to area efficiency and computational accuracy. This paper proposes a novel …

Don't throw the baby out with the bathwater: How and why deep learning for ARC
Jack Cole, Mohamed Osman
https://arxiv.org/abs/2506.14276 https://

Don't throw the baby out with the bathwater: How and why deep learning for ARC
The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful (state-of-the-art) neural networks (NN) across varied modalities and tasks in vision, language etc. The deep learning paradigm has proven to be able to train these skillful neural networks and learn the abstractions needed in these diverse domains. Our work doubles…

Continual Learning with Columnar Spiking Neural Networks
Denis Larionov, Nikolay Bazenkov, Mikhail Kiselev
https://arxiv.org/abs/2506.17169 https://…

Continual Learning with Columnar Spiking Neural Networks
This study investigates columnar-organized spiking neural networks (SNNs) for continual learning and catastrophic forgetting. Using CoLaNET (Columnar Layered Network), we show that microcolumns adapt most efficiently to new tasks when they lack shared structure with prior learning. We demonstrate how CoLaNET hyperparameters govern the trade-off between retaining old knowledge (stability) and acquiring new information (plasticity). Our optimal configuration learns ten sequential MNIST tasks effe…

Synchronization in Anonymous Networks Under Continuous Dynamics
Rida Bazzi, Anya Chaturvedi, Andr\'ea W. Richa, Peter Vargas
https://arxiv.org/abs/2506.08661

Graph signal aware decomposition of dynamic networks via latent graphs
Bishwadeep Das, Andrei Buciulea, Antonio G. Marques, Elvin Isufi
https://arxiv.org/abs/2506.08519

Graph signal aware decomposition of dynamic networks via latent graphs
Dynamics on and of networks refer to changes in topology and node-associated signals, respectively and are pervasive in many socio-technological systems, including social, biological, and infrastructure networks. Due to practical constraints, privacy concerns, or malfunctions, we often observe only a fraction of the topological evolution and associated signal, which not only hinders downstream tasks but also restricts our analysis of network evolution. Such aspects could be mitigated by moving …

🌍🛰️ How do NRENs & RRENs support Earth Observation research?
At our April infoshare with the Group on Earth Observations (GEO), RedCLARA & ASREN, we explored how R&E networks enable Earth Observation research, supporting data access, policy, training, and cross-border collaboration.
Daniela Brauner also shared these insights at GEO Global Forum 2025 last week.
📅 Don’t miss Part 2 of the infoshare series on 27 May!
🔗 Register today:

Infoshare Series on Earth Observations Support Through NRENs - Part 2

This https://arxiv.org/abs/2505.18565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
We introduce neural network architectures that combine physics-informed neural networks (PINNs) with the immersed boundary method (IBM) to solve fluid-structure interaction (FSI) problems. Our approach features two distinct architectures: a Single-FSI network with a unified parameter space, and an innovative Eulerian-Lagrangian network that maintains separate parameter spaces for fluid and structure domains. We study each architecture using standard Tanh and adaptive B-spline activation functio…

This https://arxiv.org/abs/2403.12334 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCG_…

Structural Validation Of Synthetic Power Distribution Networks Using The Multiscale Flat Norm
We study the problem of comparing a pair of geometric networks that may not be similarly defined, i.e., when they do not have one-to-one correspondences between their nodes and edges. Our motivating application is to compare power distribution networks of a region. Due to the lack of openly available power network datasets, researchers synthesize realistic networks resembling their actual counterparts. But the synthetic digital twins may vary significantly from one another and from actual netwo…

Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.
T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
…

Efficient Estimation of Word Representations in Vector Space
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Fur…

Hybrid Conference: Buddhism and the Cold War https://networks.h-net.org/group/announcements/20070100/hybrid-conference-buddhism-and-cold-war

This https://arxiv.org/abs/2505.15588 has been replaced.
initial toot: https://mastoxiv.page/@arX…

EPBench: A Benchmark for Short-term Earthquake Prediction with Neural Networks
Since the beginning of this century, the significant advancements in artificial intelligence and neural networks have offered the potential to bring new transformations to short-term earthquake prediction research. However, currently, there is no widely used benchmark for this task. To address this, we have built a new benchmark (EPBench), which is, to our knowledge, the first global regional-scale short-term earthquake prediction benchmark. Our benchmark comprises 924,472 earthquake records an…

A nice article was just published in our Focus Issue on Urban Mobility and Green Transportation in Sustainable Cities:
Active travel modelling: a methodological approach to networks for walking and cycling commuting analysis
https://iopscience.iop.org/article/10.10…

MULTISS: un protocole de stockage confidentiel {\`a} long terme sur plusieurs r{\'e}seaux QKD
Thomas Pr\'evost (I3S), Olivier Alibart (INPHYNI), Marc Kaplan, Anne Marin
https://arxiv.org/abs/2506.04800

MULTISS: un protocole de stockage confidentiel {à} long terme sur plusieurs r{é}seaux QKD
This paper presents MULTISS, a new protocol for long-term storage distributed across multiple Quantum Key Distribution (QKD) networks. This protocol is an extension of LINCOS, a secure storage protocol that uses Shamir secret sharing for secret storage on a single QKD network. Our protocol uses hierarchical secret sharing to distribute a secret across multiple QKD networks while ensuring perfect security. Our protocol further allows for sharing updates without having to reconstruct the entire s…

RCNet: $\Delta\Sigma$ IADCs as Recurrent AutoEncoders
Arnaud Verdant, William Guicquero, J\'er\^ome Chossat
https://arxiv.org/abs/2506.16903 https://…

RCNet: $ΔΣ$ IADCs as Recurrent AutoEncoders
This paper proposes a deep learning model (RCNet) for Delta-Sigma ($ΔΣ$) ADCs. Recurrent Neural Networks (RNNs) allow to describe both modulators and filters. This analogy is applied to Incremental ADCs (IADC). High-end optimizers combined with full-custom losses are used to define additional hardware design constraints: quantized weights, signal saturation, temporal noise injection, devices area. Focusing on DC conversion, our early results demonstrate that $SNR$ defined as an Effective Numb…

CHRONEX-US: City-level historical road network expansion dataset for the conterminous United States
Johannes H. Uhl, Keith A. Burghardt, Stefan Leyk
https://arxiv.org/abs/2506.16625

CHRONEX-US: City-level historical road network expansion dataset for the conterminous United States
Geospatial datasets on the long-term evolution of road networks are scarce, hampering our quantitative understanding of how the contemporary road network has evolved over the course of the 20th century. However, such information is crucial to better understand the dynamics of road network growth and expansion, and to shed light on the consequences of (sub-) urbanization processes, such as increasing mobility, traffic congestion, land take and transportation inequality. Herein, we describe CHRON…

NewsNet-SDF: Stochastic Discount Factor Estimation with Pretrained Language Model News Embeddings via Adversarial Networks
Shunyao Wang, Ming Cheng, Christina Dan Wang
https://arxiv.org/abs/2505.06864

NewsNet-SDF: Stochastic Discount Factor Estimation with Pretrained Language Model News Embeddings via Adversarial Networks
Stochastic Discount Factor (SDF) models provide a unified framework for asset pricing and risk assessment, yet traditional formulations struggle to incorporate unstructured textual information. We introduce NewsNet-SDF, a novel deep learning framework that seamlessly integrates pretrained language model embeddings with financial time series through adversarial networks. Our multimodal architecture processes financial news using GTE-multilingual models, extracts temporal patterns from macroecono…

This https://arxiv.org/abs/2412.20862 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Nonlinear reconstruction of 21cm global signal from 21cm power spectrum with artificial neural networks
In this paper, we propose a novel method to recover the 21cm global signal from the 21cm power spectrum using artificial neural networks (ANNs). The 21cm global signal is crucial for understanding cosmic evolution from the Dark Ages through the Epoch of Reionization (EoR). While interferometers like LOFAR, MWA, HERA, and SKA focus on detecting the 21cm power spectrum, single-dish experiments such as EDGES target the global signal. Our method utilizes ANNs to establish a connection between these…

Machine Learning-Based Estimation of Monthly GDP
Yonggeun Jung
https://arxiv.org/abs/2506.14078 https://arxiv.org/pdf/2506.14078

Machine Learning-Based Estimation of Monthly GDP
This paper proposes a scalable framework to estimate monthly GDP using machine learning methods. We apply Multi-Layer Perceptron (MLP), Long Short-Term Memory networks (LSTM), Extreme Gradient Boosting (XGBoost), and Elastic Net regression to map monthly indicators to quarterly GDP growth, and reconcile the outputs with actual aggregates. Using data from China, Germany, the UK, and the US, our method delivers robust performance across varied data environments. Benchmark comparisons with prior U…

This https://arxiv.org/abs/2301.06136 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantitative Verification with Neural Networks
We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic process hits a target condition within finite time. This problem subsumes a variety of quantitative verification questions, from the reachability and safety analysis of discrete-time stochastic dynamical models, to the study of assertion-violation and terminatio…

The effects of initial conditions on the accuracy of mean-field approximations of Markov processes on large random graphs
Pierfrancesco Dionigi, D\'aniel Keliger
https://arxiv.org/abs/2506.12872

The effects of initial conditions on the accuracy of mean-field approximations of Markov processes on large random graphs
We study the evolution of a general class of stochastic processes (containing, e.g. SIS and SIR models) on large random networks, focusing on a particular general class of random graph models. To approximate the expected dynamics of these processes, we employ a mean-field technique known as the N-Intertwined Mean-Field Approximation (NIMFA). Our primary goal is to quantify the impact of the randomness in the network topology on the accuracy of such approximations. While classical work by Kurtz …

Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi
Andrey Derzhavin, Denis Larionov
https://arxiv.org/abs/2506.18306 https://

Spiffy: Efficient Implementation of CoLaNET for Raspberry Pi
This paper presents a lightweight software-based approach for running spiking neural networks (SNNs) without relying on specialized neuromorphic hardware or frameworks. Instead, we implement a specific SNN architecture (CoLaNET) in Rust and optimize it for common computing platforms. As a case study, we demonstrate our implementation, called Spiffy, on a Raspberry Pi using the MNIST dataset. Spiffy achieves 92% accuracy with low latency - just 0.9 ms per training step and 0.45 ms per inference …

Emerging Networks and Services in Developing Nations -- Barbados Use Case
Warren Scantlebury, Milena Radenkovic
https://arxiv.org/abs/2506.13934 https://…

Emerging Networks and Services in Developing Nations -- Barbados Use Case
This report aims to conduct an in-depth comparison of DTN (Delay/Disconnection Tolerant Network) performance and characteristics in the developing country of Barbados versus two major UK cities Nottingham and London. We aim to detect any common patterns or deviations between the two region areas and use the results of our network simulations to draw well-founded conclusions on the reasons for these similarities and differences. In the end we hope to be able to assimilate specific portions of th…

Adaptive Cucker-Smale Networks: Limiting Laplacian Time-Varying Dynamics
Christian Kuehn, Jaeyoung Yoon
https://arxiv.org/abs/2506.06131 https://

Adaptive Cucker-Smale Networks: Limiting Laplacian Time-Varying Dynamics
Differences in opinion can be seen as distances between individuals, and such differences do not always vanish over time. In this paper, we propose a modeling framework that captures the formation of opinion clusters, based on extensions of the Cucker Smale and Hegselmann Krause models to a combined adaptive (or co-evolutionary) network. Reducing our model to a singular limit of fast adaptation, we mathematically analyze the asymptotic behavior of the resulting Laplacian dynamics over various c…

What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
Lance Ying, Daniel Xu, Alicia Zhang, Katherine M. Collins, Max H. Siegel, Joshua B. Tenenbaum
https://arxiv.org/abs/2506.14212

What's in the Box? Reasoning about Unseen Objects from Multimodal Cues
People regularly make inferences about objects in the world that they cannot see by flexibly integrating information from multiple sources: auditory and visual cues, language, and our prior beliefs and knowledge about the scene. How are we able to so flexibly integrate many sources of information to make sense of the world around us, even if we have no direct knowledge? In this work, we propose a neurosymbolic model that uses neural networks to parse open-ended multimodal inputs and then applie…

DBNets2.0: simulation-based inference for planet-induced dust substructures in protoplanetary discs
A. Ruzza, G. Lodato, G. P. Rosotti, P. J. Armitage
https://arxiv.org/abs/2506.11200

DBNets2.0: simulation-based inference for planet-induced dust substructures in protoplanetary discs
Dust substructures in protoplanetary discs can be signatures of embedded young planets whose detection and characterisation would provide a better understanding of planet formation. Traditional techniques used to link substructures' morphology to the properties of putative embedded planets present several limitations that the use of deep learning methods has partly overcome. In our previous work, we developed DBNets, a tool exploiting an ensemble of Convolutional Neural Networks (CNNs) to estim…

Corrections to Friis noise factor formulas for cascade networks
Ankitha E Bangera
https://arxiv.org/abs/2506.09900 https://arxiv.org/…

Corrections to Friis noise factor formulas for cascade networks
The signal-to-noise ratio of a multistage cascade network is often estimated using the well-known Friis' formulas for noise factors (or the noise figures in decibels). However, this article addresses the major errors in Friis' noise factor formulas for higher stages. Additionally, we re-derive the correct formulas to calculate the stage-wise noise factors for cascade networks from the basic definition of noise factors. We then present a comparison of our derived formulas with Friis' noise facto…

This https://arxiv.org/abs/2408.03431 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Compactifications of phylogenetic systems and species of electrical networks
We describe new spaces and maps. Our graphical map is a visual and numerical correspondence between spaces of circular electrical networks and circular planar split systems. When restricted to the planar circular electrical case, this graphical map finds the split system uniquely associated with the Kalmanson resistance distance of the dual network, matching the induced split system familiar from phylogenetics. This correspondence is extended to compactifications of the respective spaces, takin…

Entangled Interlocked Diamond-like (Diamondiynes) Lattices
C. M. O. Bastos, E. J. A. dos Santos, R. A. F. Alves, Alexandre C. Dias, L. A. Ribeiro Junior, D. S. Galv\~ao
https://arxiv.org/abs/2506.10181

Entangled Interlocked Diamond-like (Diamondiynes) Lattices
Diamondynes, a new class of diamond-like carbon allotropes composed of carbon with sp$^2$/sp$^3$-hybridized carbon networks, exhibit unique structural motifs that have not been previously reported in carbon materials. These architectures feature sublattices that are both interlocked and capable of relative movement. Using ab initio simulations, we have conducted an extensive investigation into the structural and electronic properties of five diamondyne structures. Our results show that diamondi…

Panel on Tibetan Yoga at the 17th Seminar of the International Association of Tibetan Studies (Kathmandu, August 23-29, 2026) https://networks.h-net.org/group/announcements/20070110/panel-tibetan-yoga-17th-seminar-internatio…

Improved Image Reconstruction and Diffusion Parameter Estimation Using a Temporal Convolutional Network Model of Gradient Trajectory Errors
Jonathan B. Martin, Hannah E. Alderson, John C. Gore, Mark D. Does, Kevin D. Harkins
https://arxiv.org/abs/2506.14995

Improved Image Reconstruction and Diffusion Parameter Estimation Using a Temporal Convolutional Network Model of Gradient Trajectory Errors
Summary: Errors in gradient trajectories introduce significant artifacts and distortions in magnetic resonance images, particularly in non-Cartesian imaging sequences, where imperfect gradient waveforms can greatly reduce image quality. Purpose: Our objective is to develop a general, nonlinear gradient system model that can accurately predict gradient distortions using convolutional networks. Methods: A set of training gradient waveforms were measured on a small animal imaging system, and used …

Fully-Distributed Construction of Byzantine-Resilient Dynamic Peer-to-Peer Networks
Aayush Gupta, Gopal Pandurangan
https://arxiv.org/abs/2506.04368 https:…

Fully-Distributed Construction of Byzantine-Resilient Dynamic Peer-to-Peer Networks
We address a fundamental problem in Peer-to-Peer (P2P) networks, namely, constructing and maintaining dynamic P2P overlay network topologies with essential properties such as connectivity, low diameter, and high expansion, that are resilient to continuous high churn and the presence of a large number of malicious (Byzantine) nodes. Our main goal is to construct and maintain a sparse (bounded degree) expander topology despite high churn and a large number of Byzantine nodes. Such an expander top…

This https://arxiv.org/abs/2412.01625 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Aubry Set of Eikonal Hamilton-Jacobi Equations on Networks
We extend the study of eikonal Hamilton-Jacobi equations posed on networks performed by Siconolfi and Sorrentino (Anal. PDE, 2018) to a more general setting. Their approach essentially exploits that such equations correspond to discrete problems on an abstract underlying graph. However, a specific condition they assume can be rather restricting in some settings, which motivates the generalization we propose. We still get an Aubry set, which plays the role of a uniqueness set for our problem and…

Deep Learning Enhanced Multi-Day Turnover Quantitative Trading Algorithm for Chinese A-Share Market
Yimin Du
https://arxiv.org/abs/2506.06356 https://

Deep Learning Enhanced Multi-Day Turnover Quantitative Trading Algorithm for Chinese A-Share Market
This paper presents a sophisticated multi-day turnover quantitative trading algorithm that integrates advanced deep learning techniques with comprehensive cross-sectional stock prediction for the Chinese A-share market. Our framework combines five interconnected modules: initial stock selection through deep cross-sectional prediction networks, opening signal distribution analysis using mixture models for arbitrage identification, market capitalization and liquidity-based dynamic position sizing…

✨ Spring SIGs wrapped! ✨
From Prague to Paris to Ispra, 4 GÉANT Special Interest Groups (SIGs) met to explore AI, Time & Frequency networks, service strategy development, and network operations.
Spring days packed with great ideas, useful insights, new collaborations, and our beloved Lightning Talks.
👏 Big thanks to CESNET, RENATER, EC JRC & all who joined in-person and online.
Catch up on all the highlights and takeaways here 👉

GÉANT Community Programme | GÉANT CONNECT Online
The GÉANT community programme supports research and education through the activities of Special Interest Groups and Task Forces and connects academia, the business community and governmental organisations.

Goal-Oriented Semantic Resource Allocation with Cumulative Prospect Theoretic Agents
Symeon Vaidanis, Photios A. Stavrou, Marios Kountouris
https://arxiv.org/abs/2506.04947

Goal-Oriented Semantic Resource Allocation with Cumulative Prospect Theoretic Agents
We introduce a resource allocation framework for goal-oriented semantic networks, where participating agents assess system quality through subjective (e.g., context-dependent) perceptions. To accommodate this, our model accounts for agents whose preferences deviate from traditional expected utility theory (EUT), specifically incorporating cumulative prospect theory (CPT) preferences. We develop a comprehensive analytical framework that captures human-centric aspects of decision-making and risky…

CNN-Enabled Scheduling for Probabilistic Real-Time Guarantees in Industrial URLLC
Eman Alqudah, Ashfaq Khokhar
https://arxiv.org/abs/2506.14987 https://

CNN-Enabled Scheduling for Probabilistic Real-Time Guarantees in Industrial URLLC
Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a CNN-based dynamic priority prediction mechanism for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach uses a Convolutional Neural Network and graph coloring to adaptively assign link priorities based on r…

Vector Representations of Vessel Trees
James Batten, Michiel Schaap, Matthew Sinclair, Ying Bai, Ben Glocker
https://arxiv.org/abs/2506.11163 https://

Vector Representations of Vessel Trees
We introduce a novel framework for learning vector representations of tree-structured geometric data focusing on 3D vascular networks. Our approach employs two sequentially trained Transformer-based autoencoders. In the first stage, the Vessel Autoencoder captures continuous geometric details of individual vessel segments by learning embeddings from sampled points along each curve. In the second stage, the Vessel Tree Autoencoder encodes the topology of the vascular network as a single vector r…

A network of parametrically driven silicon nitride mechanical membranes
Luis Mestre, Suyash Singh, Gabriel Margiani, Letizia Catalini, Alexander Eichler, Vincent Dumont
https://arxiv.org/abs/2506.00850

A network of parametrically driven silicon nitride mechanical membranes
Networks of nonlinear resonators offer a promising platform for analog computing and the emulation of complex systems. However, realizing such networks remains challenging, as it requires resonators with high quality factors, individual frequency tunability, and strong inter-resonator coupling. In this work, we present a system that meets all these criteria. Our system is based on metallized silicon nitride membranes that are coupled via their common substrate and controlled capacitively via el…

GATE: Geometry-Aware Trained Encoding
Jakub Bok\v{s}ansk\'y, Daniel Meister, Carsten Benthin
https://arxiv.org/abs/2506.08161 https://

GATE: Geometry-Aware Trained Encoding
The encoding of input parameters is one of the fundamental building blocks of neural network algorithms. Its goal is to map the input data to a higher-dimensional space, typically supported by trained feature vectors. The mapping is crucial for the efficiency and approximation quality of neural networks. We propose a novel geometry-aware encoding called GATE that stores feature vectors on the surface of triangular meshes. Our encoding is suitable for neural rendering-related algorithms, for exa…

Embedded Acoustic Intelligence for Automotive Systems
Renjith Rajagopal, Peter Winzell, Sladjana Strbac, Konstantin Lindstr\"om, Petter H\"orling, Faisal Kohestani, Niloofar Mehrzad
https://arxiv.org/abs/2506.11071

Embedded Acoustic Intelligence for Automotive Systems
Transforming sound insights into actionable streams of data, this abstract leverages findings from degree thesis research to enhance automotive system intelligence, enabling us to address road type [1].By extracting and interpreting acoustic signatures from microphones installed within the wheelbase of a car, we focus on classifying road type.Utilizing deep neural networks and feature extraction powered by pre-trained models from the Open AI ecosystem (via Hugging Face [2]), our approach enable…

Adversarial control of synchronization in complex oscillator networks
Yasutoshi Nagahama, Kosuke Miyazato, Kazuhiro Takemoto
https://arxiv.org/abs/2506.02403

Adversarial control of synchronization in complex oscillator networks
This study investigates adversarial attacks, a concept from deep learning, designed to control synchronization dynamics through strategically crafted minimal perturbations. We propose a gradient-based optimization method that identifies small phase perturbations to dramatically enhance or suppress collective synchronization in Kuramoto oscillator networks. Our approach formulates synchronization control as an adversarial optimization problem, computing gradients of the order parameter with resp…

This https://arxiv.org/abs/2402.16887 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

A Comprehensive Survey on Artificial Intelligence for Complex Network: Potential, Methodology and Application
Complex networks pervade various real-world systems, from the natural environment to human societies. The essence of these networks is in their ability to transition and evolve from microscopic disorder-where network topology and node dynamics intertwine-to a macroscopic order characterized by certain collective behaviors. Over the past two decades, complex network science has significantly enhanced our understanding of the statistical mechanics, structures, and dynamics underlying real-world n…

Self-orthogonalizing attractor neural networks emerging from the free energy principle
Tamas Spisak, Karl Friston
https://arxiv.org/abs/2505.22749 https://…

Self-orthogonalizing attractor neural networks emerging from the free energy principle
Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from first principles is crucial for advancing our understanding of neuronal computations and the design of artificial intelligence systems. Here we formalize how attractor networks emerge from the free energy principle applied to a universal partitioning of random dynamical systems. Our approach obviates the need for explicitly imposed learning and inference ru…

Synaptic shot-noise triggers fast and slow global oscillations in balanced neural networks
Denis S. Goldobin, Maria V. Ageeva, Matteo di Volo, Ferdinand Tixidre, Alessandro Torcini
https://arxiv.org/abs/2505.22373

Synaptic shot-noise triggers fast and slow global oscillations in balanced neural networks
Neural dynamics is determined by the transmission of discrete synaptic pulses (synaptic shot-noise) among neurons. However, the neural responses are usually obtained within the diffusion approximation modeling synaptic inputs as continuous Gaussian noise. Here, we present a rigorous mean-field theory that encompasses synaptic shot-noise for sparse balanced inhibitory neural networks driven by an excitatory drive. Our theory predicts new dynamical regimes, in agreement with numerical simulations…

Functional second-order Gaussian Poincar\'e inequalities
Anna Vidotto, Guangqu Zheng
https://arxiv.org/abs/2506.13571 https://arx…

Functional second-order Gaussian Poincaré inequalities
In this paper, we work in the framework of Hilbert-valued Wiener structures and derive a functional version of the second-order Gaussian Poincaré inequality that leads to abstract bounds for Gaussian process approximation in $d_2$ distance. Our abstract bounds are flexible and can be applied in various examples including functional Breuer-Major central limit theorems, shallow neural networks, and spatial statistics of SPDEs solutions.

Empirical Quantification of Spurious Correlations in Malware Detection
Bianca Perasso, Ludovico Lozza, Andrea Ponte, Luca Demetrio, Luca Oneto, Fabio Roli
https://arxiv.org/abs/2506.09662

Empirical Quantification of Spurious Correlations in Malware Detection
End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep networks mainly focus on metadata, none investigated the phenomenon further, without quantifying their impact on the decision. In this work, we deepen our understanding of how spurious correlation affects d…

Trade Networks and the Rise of a Global Currency
Tomoo Kikuchi, Lien Pham
https://arxiv.org/abs/2505.22080 https://arxiv.org/pdf/2505…

Trade Networks and the Rise of a Global Currency
We develop a model of strategic competition between global currencies. Issuers choose their commitment levels for currency internationalization, while users -- interconnected in a trade network -- choose their usage of each currency for trade settlement. Our theoretical findings highlight not only the advantage of the status-quo issuer in maintaining dominance, but also the conditions under which an emerging issuer can attract users, potentially leading to a multi-currency payment system. The n…

Was Residual Penalty and Neural Operators All We Needed for Solving Optimal Control Problems?
Oliver G. S. Lundqvist, Fabricio Oliveira
https://arxiv.org/abs/2506.04742

Was Residual Penalty and Neural Operators All We Needed for Solving Optimal Control Problems?
Neural networks have been used to solve optimal control problems, typically by training neural networks using a combined loss function that considers data, differential equation residuals, and objective costs. We show that including cost functions in the training process is unnecessary, advocating for a simpler architecture and streamlined approach by decoupling the optimal control problem from the training process. Thus, our work shows that a simple neural operator architecture, such as DeepON…

GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
Eman Alqudah, Ashfaq Khokhar
https://arxiv.org/abs/2506.15011 …

GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph Convolutional Network (GCN) integrated with a Deep Q-Network (DQN) reinforcement learning framework for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach dynamically learns link priorities based on …

Attractor learning for spatiotemporally chaotic dynamical systems using echo state networks with transfer learning
Mohammad Shah Alam, William Ott, Ilya Timofeyev
https://arxiv.org/abs/2505.24099

Attractor learning for spatiotemporally chaotic dynamical systems using echo state networks with transfer learning
In this paper, we explore the predictive capabilities of echo state networks (ESNs) for the generalized Kuramoto-Sivashinsky (gKS) equation, an archetypal nonlinear PDE that exhibits spatiotemporal chaos. We introduce a novel methodology that integrates ESNs with transfer learning, aiming to enhance predictive performance across various parameter regimes of the gKS model. Our research focuses on predicting changes in long-term statistical patterns of the gKS model that result from varying the d…

Hybrid Conference> Buddhism and the Cold War, June 27 https://networks.h-net.org/group/announcements/20070101/hybrid-conference-buddhism-and-cold-war

Physics-Informed Neural Networks for the Relativistic Burgers Equation in the Exterior of a Schwarzschild Black Hole
Shuyang Xiang
https://arxiv.org/abs/2506.00951

Physics-Informed Neural Networks for the Relativistic Burgers Equation in the Exterior of a Schwarzschild Black Hole
We introduce a Physics-Informed Neural Networks(PINN) to solve a relativistic Burgers equation in the exterior domain of a Schwarzschild black hole. Our main contribution is a PINN architecture that is able to simulate shock wave formations in such curved spacetime, by training a shock- aware network block and introducing a Godunov-inspired residuals in the loss function. We validate our method with numerical experiments with different kinds of initial conditions. We show its ability to reprodu…

This https://arxiv.org/abs/2412.10580 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

DeepWiener: Neural Networks for CMB polarization maps and power spectrum computation
To study the early Universe, it is essential to estimate cosmological parameters with high accuracy, which depends on the optimal reconstruction of Cosmic Microwave Background (CMB) maps and the measurement of their power spectrum. In this paper, we generalize the neural network developed for applying the Wiener Filter, initially presented for temperature maps in previous work, to polarization maps. Our neural network has a UNet architecture, including an extra channel for the noise variance ma…

Joint Routing and Control Optimization in VANET
Chen Huang, Dingxuan Wang, Ronghui Hou
https://arxiv.org/abs/2506.08038 https://arxiv…

Joint Routing and Control Optimization in VANET
In this paper, we introduce DynaRoute, an adaptive joint optimization framework for dynamic vehicular networks that simultaneously addresses platoon control and data transmission through trajectory-aware routing and safety-constrained vehicle coordination. DynaRoute guarantees continuous vehicle movement via platoon safety control with optimizing transmission paths through real-time trajectory prediction and ensuring reliable data. Our solution achieves three key objectives: (1) maintaining pla…

Adaptive determinantal scheduling with fairness in wireless networks
H. P. Keeler, B. B{\l}aszczyszyn
https://arxiv.org/abs/2506.11738 https://

Adaptive determinantal scheduling with fairness in wireless networks
We propose a novel framework for wireless network scheduling with fairness using determinantal (point) processes. Our approach incorporates the repulsive nature of determinantal processes, generalizing traditional Aloha protocols that schedule transmissions independently. We formulate the scheduling problem with an utility function representing fairness. We then recast this formulation as a convex optimization problem over a certain class of determinantal point processes called $L$-ensembles, w…

CFP> Panel on Tibetan Yoga at the 17th Seminar of the International Association of Tibetan Studies (Kathmandu, August 23-29, 2026) https://networks.h-net.org/group/announcements/20070111/panel-tibetan-yoga-17th-seminar-in…

This https://arxiv.org/abs/2308.13135 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery
We propose a nonparametric additive model for estimating interpretable value functions in reinforcement learning, with an application in optimizing postoperative recovery through personalized, adaptive recommendations. While reinforcement learning has achieved significant success in various domains, recent methods often rely on black-box approaches such as neural networks, which hinder the examination of individual feature contributions to a decision-making policy. Our novel method offers a fle…

This https://arxiv.org/abs/2501.00417 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

PureRank: A Parameter-Free Recursive Importance Measure for Network Nodes
Classical parameter-free centrality measures based on the recursive definition of importance (RDI), such as eigenvector centrality and Seeley centrality, are limited to strongly connected networks, while widely used methods like Katz centrality and PageRank rely on free parameters, such as the damping factor, to handle general networks. This motivates our central question: can an RDI-based importance (centrality) measure be defined for arbitrary networks without any tunable parameters? We answe…

Transport Network, Graph, and Air Pollution
Nan Xu
https://arxiv.org/abs/2506.01164 https://arxiv.org/pdf/2506.01164

Transport Network, Graph, and Air Pollution
Air pollution can be studied in the urban structure regulated by transport networks. Transport networks can be studied as geometric and topological graph characteristics through designed models. Current studies do not offer a comprehensive view as limited models with insufficient features are examined. Our study finds geometric patterns of pollution-indicated transport networks through 0.3 million image interpretations of global cities. These are then described as part of 12 indices to investig…

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor
Rishit Dagli, Yushi Guan, Sankeerth Durvasula, Mohammadreza Mofayezi, Nandita Vijaykumar
https://arxiv.org/abs/2506.07932

Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor
We propose Squeeze3D, a novel framework that leverages implicit prior knowledge learnt by existing pre-trained 3D generative models to compress 3D data at extremely high compression ratios. Our approach bridges the latent spaces between a pre-trained encoder and a pre-trained generation model through trainable mapping networks. Any 3D model represented as a mesh, point cloud, or a radiance field is first encoded by the pre-trained encoder and then transformed (i.e. compressed) into a highly com…

This https://arxiv.org/abs/2503.00993 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepp…

Exploring fully-heavy tetraquarks through the CGAN framework: Mass and width
Fully-heavy tetraquark states, $QQ\bar{Q}\bar{Q} (Q=c,b)$, have garnered significant attention both experimentally and theoretically, due to their unique properties and potential to provide new insights into Quantum Chromodynamics (QCD). In this study, we employ Conditional Generative Adversarial Networks (CGANs) to predict the masses and decay widths of fully-heavy tetraquarks. To deepen our understanding of heavy multiquark structures, we prepare datasets based on two distinct approaches and …

This https://arxiv.org/abs/2506.00951 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Physics-Informed Neural Networks for the Relativistic Burgers Equation in the Exterior of a Schwarzschild Black Hole
We introduce a Physics-Informed Neural Networks(PINN) to solve a relativistic Burgers equation in the exterior domain of a Schwarzschild black hole. Our main contribution is a PINN architecture that is able to simulate shock wave formations in such curved spacetime, by training a shock- aware network block and introducing a Godunov-inspired residuals in the loss function. We validate our method with numerical experiments with different kinds of initial conditions. We show its ability to reprodu…

ONLINE WORKSHOP> Navigating Indra’s Net: Digital Approaches to Text Reuse-based Inter-textuality in Pre-Modern East Asian Texts https://networks.h-net.org/group/announcements/20069984/navigating-indras-net-digital-approache…

Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity
Jun-Pyo Hong, Hyowoon Seo, Kisong Lee
https://arxiv.org/abs/2506.06090

Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity
The conventional FL methods face critical challenges in realistic wireless edge networks, where training data is both limited and heterogeneous, often leading to unstable training and poor generalization. To address these challenges in a principled manner, we propose a novel wireless FL framework grounded in Bayesian inference. By virtue of the Bayesian approach, our framework captures model uncertainty by maintaining distributions over local weights and performs distribution-level aggregation …

This https://arxiv.org/abs/2505.05358 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

Empirical Analysis of Transaction Conflicts in Ethereum and Solana for Parallel Execution
This paper presents a comprehensive analysis of historical data across two popular blockchain networks: Ethereum and Solana. Our study focuses on two key aspects: transaction conflicts and the maximum theoretical parallelism within historical blocks. We aim to quantify the degree of transaction parallelism and assess how effectively it can be exploited by systematically examining block-level characteristics, both within individual blocks and across different historical periods. In particular, t…

This https://arxiv.org/abs/2501.00417 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

PureRank: A Parameter-Free Recursive Importance Measure for Network Nodes
Classical parameter-free centrality measures based on the recursive definition of importance (RDI), such as eigenvector centrality and Seeley centrality, are limited to strongly connected networks, while widely used methods like Katz centrality and PageRank rely on free parameters, such as the damping factor, to handle general networks. This motivates our central question: can an RDI-based importance (centrality) measure be defined for arbitrary networks without any tunable parameters? We answe…

World Genealogy: Knowledge, Kinship and Ancestors in Global and Historical Perspective (June 2026 / Hamburg, Germany) https://networks.h-net.org/group/announcements/20069800/world-genealogy-knowledge-kinship-and-ancestor…

This https://arxiv.org/abs/2502.17433 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Dynamical phases of short-term memory mechanisms in RNNs
Short-term memory is essential for cognitive processing, yet our understanding of its neural mechanisms remains unclear. Neuroscience has long focused on how sequential activity patterns, where neurons fire one after another within large networks, can explain how information is maintained. While recurrent connections were shown to drive sequential dynamics, a mechanistic understanding of this process still remains unknown. In this work, we introduce two unique mechanisms that can support this f…

Robust Distribution Network Reconfiguration Using Mapping-based Column-and-Constraint Generation
Runjie Zhang, Kaiping Qu, Changhong Zhao, Wanjun Huang
https://arxiv.org/abs/2505.24677

Robust Distribution Network Reconfiguration Using Mapping-based Column-and-Constraint Generation
The integration of intermittent renewable energy sources into distribution networks introduces significant uncertainties and fluctuations, challenging their operational security, stability, and efficiency. This paper considers robust distribution network reconfiguration (RDNR) with renewable generator resizing, modeled as a two-stage robust optimization (RO) problem with decision-dependent uncertainty (DDU). Our model optimizes resizing decisions as the upper bounds of renewable generator outpu…

This https://arxiv.org/abs/2504.08335 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Entropic bounds for conditionally Gaussian vectors and applications to neural networks
Using entropic inequalities from information theory, we provide new bounds on the total variation and 2-Wasserstein distances between a conditionally Gaussian law and a Gaussian law with invertible covariance matrix. We apply our results to quantify the speed of convergence to Gaussian of a randomly initialized fully connected neural network and its derivatives - evaluated in a finite number of inputs - when the initialization is Gaussian and the sizes of the inner layers diverge to infinity. O…

CFP> World Genealogy: Knowledge, Kinship and Ancestors in Global and Historical Perspective (June 2026 / Hamburg, Germany) https://networks.h-net.org/group/announcements/20069799/world-genealogy-knowledge-kinship-and-…

Interference-Aware Multiuser Hybrid Precoding for Coexistence with LEO Satellite Communication
Nima Razavi, Murat Bayraktar, Nuria Gonzalez Prelcic, Robert W. Heath Jr
https://arxiv.org/abs/2506.03438

Interference-Aware Multiuser Hybrid Precoding for Coexistence with LEO Satellite Communication
Interference from terrestrial networks can reduce the communication rate for low Earth orbit (LEO) satellites in the upper mid-band. To coexist in frequency, MIMO precoding can be used to reduce the signal that impinges on the LEO satellite. We present a beamforming algorithm designed for the hybrid architecture that incorporates a satellite interference penalty while optimizing the analog and digital precoders. Our algorithm optimizes the precoding at the base station (BS) within the set of pr…

This https://arxiv.org/abs/2412.07901 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Homophily Within and Across Groups
Homophily-the tendency to connect with similar others-plays a central role in shaping network structure and function. It is often treated as a uniform, global parameter, independent from other structural features. Here, we propose a maximum-entropy framework that decomposes homophily into contributions within and across groups, with the stochastic block model emerging as a special case. Our exponential-family formulation, parameterized by group size, fits real-world social networks well and all…

Deep Learning-Based CSI Feedback for Wi-Fi Systems With Temporal Correlation
Junyong Shin, Eunsung Jeon, Inhyoung Kim, Yo-Seb Jeon
https://arxiv.org/abs/2505.23198

Deep Learning-Based CSI Feedback for Wi-Fi Systems With Temporal Correlation
To achieve higher throughput in next-generation Wi-Fi systems, a station (STA) needs to efficiently compress channel state information (CSI) and feed it back to an access point (AP). In this paper, we propose a novel deep learning (DL)-based CSI feedback framework tailored for next-generation Wi-Fi systems. Our framework incorporates a pair of encoder and decoder neural networks to compress and reconstruct the angle parameters of the CSI. To enable an efficient finite-bit representation of the …

Video Quality Monitoring for Remote Autonomous Vehicle Control
Dimitrios Kafetzis, Nikos Fotiou, Savvas Argyropoulos, Jad Nasreddine, Iordanis Koutsopoulos
https://arxiv.org/abs/2506.03166

Video Quality Monitoring for Remote Autonomous Vehicle Control
The delivery of high-quality, low-latency video streams is critical for remote autonomous vehicle control, where operators must intervene in real time. However, reliable video delivery over Fourth/Fifth-Generation (4G/5G) mobile networks is challenging due to signal variability, mobility-induced handovers, and transient congestion. In this paper, we present a comprehensive blueprint for an integrated video quality monitoring system, tailored to remote autonomous vehicle operation. Our proposed …

B2LoRa: Boosting LoRa Transmission for Satellite-IoT Systems with Blind Coherent Combining
Yimin Zhao, Weibo Wang, Xiong Wang, Linghe Kong, Jiadi Yu, Yifei Zhu, Shiyuan Li, Chong He, Guihai Chen
https://arxiv.org/abs/2505.24140

B2LoRa: Boosting LoRa Transmission for Satellite-IoT Systems with Blind Coherent Combining
With the rapid growth of Low Earth Orbit (LEO) satellite networks, satellite-IoT systems using the LoRa technique have been increasingly deployed to provide widespread Internet services to low-power and low-cost ground devices. However, the long transmission distance and adverse environments from IoT satellites to ground devices pose a huge challenge to link reliability, as evidenced by the measurement results based on our real-world setup. In this paper, we propose a blind coherent combining d…