Tootfinder

Apple's machine learning research team quietly releases MLX, an array framework to train and deploy ML models on Apple silicon, available on GitHub (Jonny Evans/Computerworld)
https://www.computerworld.com/article/3711

Apple launches MLX machine-learning framework for Apple Silicon
Apple’s machine learning (ML) teams quietly flexed their muscle with the release of a new ML framework developed for Apple Silicon.

Today's Bird Note Radio episode:
Using Machine Learning to Forecast Bird Migration (less than two-minute podcast).
https://www.birdnote.org/listen/shows/using-machine-learning-forecast-bird-migration

Using Machine Learning to Forecast Bird Migration | BirdNote
AI helps make advances — but it relies on human scientists

Enhancing Malware Detection by Integrating Machine Learning with Cuckoo Sandbox
Amaal F. Alshmarni, Mohammed A. Alliheedi
https://arXiv.org/abs/2311.04372 …

Enhancing Malware Detection by Integrating Machine Learning with Cuckoo Sandbox
In the modern era, malware is experiencing a significant increase in both its variety and quantity, aligning with the widespread adoption of the digital world. This surge in malware has emerged as a critical challenge in the realm of cybersecurity, prompting numerous research endeavors and contributions to address the issue. Machine learning algorithms have been leveraged for malware detection due to their ability to uncover concealed patterns within vast datasets. However, deep learning algori…

This https://arxiv.org/abs/2310.02854 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Multi-Domain Causal Representation Learning via Weak Distributional Invariances
Causal representation learning has emerged as the center of action in causal machine learning research. In particular, multi-domain datasets present a natural opportunity for showcasing the advantages of causal representation learning over standard unsupervised representation learning. While recent works have taken crucial steps towards learning causal representations, they often lack applicability to multi-domain datasets due to over-simplifying assumptions about the data; e.g. each domain com…

Identification of Galaxy–Galaxy Strong #Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning: https://iopscience.iop.org/article/10.3847/1538-4357/ace4ba -> An international research collaboration trained computers to sift through millions of images for cosmic treasure: https://skyandtelescope.org/astronomy-news/astronomers-discover-562-new-candidate-strong-lenses-with-machine-learning/

Machine Learning mit Python – KI und Deep Learning in 5 Webinaren erklärt
Ab dem 11.01. lernen Sie in fünf Webinaren, die Welt der künstlichen Intelligenz kennen. Von Machine Learning über neuronale Netze bis zu Deep Learning.

Apple's machine learning research team quietly releases MLX, an array framework to train and deploy ML models on Apple silicon, available on GitHub (Jonny Evans/Computerworld)
https://www.computerworld.com/article/3711

Apple launches MLX machine-learning framework for Apple Silicon
Apple’s machine learning (ML) teams quietly flexed their muscle with the release of a new ML framework developed for Apple Silicon.

Thoughtful angle on the end of #Jezebel:
"... we have spent days or weeks on an in-depth investigation, published that investigation, been thanked by readers for shedding light on an issue they didn’t know about, been aggregated by our peers in the industry, & then have learned later that our article was deemed as unsuitable for programmatic advertising by a machine learning algorithm. This is the landscape that Jezebel & every other news outlet is playing in."
#media

Abeba Birhane on AI hype
https://www.siliconrepublic.com/future-human/abeba-birhane-generative-ai-chatgpt-openai-machine-learning

Dr Abeba Birhane highlights the dangers of hyping up generative AI
Dr Abeba Birhane discussed the limitations and misconceptions that cloud the AI conversation in an in-depth chat with Jenny Darmody.

This https://arxiv.org/abs/2309.13546 has been replaced.
Link: https://scholar.google.com/scholar?q=a

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
Federated Learning (FL) is a privacy-constrained decentralized machine learning paradigm in which clients enable collaborative training without compromising private data. However, how to learn a robust global model in the data-heterogeneous and model-heterogeneous FL scenarios is challenging. To address it, we resort to data-free knowledge distillation to propose a new FL method (namely DFRD). DFRD equips a conditional generator on the server to approximate the training space of the local model…

This https://arxiv.org/abs/2306.04843 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Classical Verification of Quantum Learning
Quantum data access and quantum processing can make certain classically intractable learning tasks feasible. However, quantum capabilities will only be available to a select few in the near future. Thus, reliable schemes that allow classical clients to delegate learning to untrusted quantum servers are required to facilitate widespread access to quantum learning advantages. Building on a recently introduced framework of interactive proof systems for classical machine learning, we develop a fram…

Two Watts is All You Need: Enabling In-Detector Real-Time Machine Learning for Neutrino Telescopes Via Edge Computing
Miaochen Jin, Yushi Hu, Carlos A. Argüelles
https://arXiv.org/abs/2311.04983

Two Watts is All You Need: Enabling In-Detector Real-Time Machine Learning for Neutrino Telescopes Via Edge Computing
The use of machine learning techniques has significantly increased the physics discovery potential of neutrino telescopes. In the upcoming years, we are expecting upgrade of currently existing detectors and new telescopes with novel experimental hardware, yielding more statistics as well as more complicated data signals. This calls out for an upgrade on the software side needed to handle this more complex data in a more efficient way. Specifically, we seek low power and fast software methods to…

Enabling next-generation AI workloads: Announcing TPU v5p and AI Hypercomputer
https://cloud.google.com/blog/products/ai-machine-learning/introducing-cloud-tpu-v5p-and-ai-hypercomputer
HN:

Introducing Cloud TPU v5p and AI Hypercomputer | Google Cloud Blog
The new TPU v5p is a core element of AI Hypercomputer, which is tuned, managed, and orchestrated specifically for gen AI training and serving.

Core determinants of quality criteria for mhealth for hypertension: evidence from machine learning instruments
Danielly de Paula, Ariane Sasso, Justus Coester, Erwin Boettinger
https://arXiv.org/abs/2311.05434

Core determinants of quality criteria for mhealth for hypertension: evidence from machine learning instruments
Uncontrolled hypertension is a global problem that needs to be addressed. Despite the many mHealth solutions in the market, the nonadherence relative to intended use jeopardizes treatment success. Although investigating user experience is one of the most important mechanisms for understanding mHealth discontinuance, surprisingly, the core determinants of overall user experience (i.e., positive and negative) about mHealth apps for hypertension are unknown. To address the mentioned gap in knowled…

Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
Su Wang, Roberto Morabito, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton
https://arXiv.org/abs/2311.04350

Device Sampling and Resource Optimization for Federated Learning in Cooperative Edge Networks
The conventional federated learning (FedL) architecture distributes machine learning (ML) across worker devices by having them train local models that are periodically aggregated by a server. FedL ignores two important characteristics of contemporary wireless networks, however: (i) the network may contain heterogeneous communication/computation resources, and (ii) there may be significant overlaps in devices' local data distributions. In this work, we develop a novel optimization methodology th…

Today's Bird Note Radio episode:
Using Machine Learning to Forecast Bird Migration (less than two-minute podcast).
https://www.birdnote.org/listen/shows/using-machine-learning-forecast-bird-migration

Using Machine Learning to Forecast Bird Migration | BirdNote
AI helps make advances — but it relies on human scientists

This https://arxiv.org/abs/2301.09633 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Prediction-Powered Inference
Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms for computing provably valid confidence intervals for quantities such as means, quantiles, and linear and logistic regression coefficients, without making any assumptions on the machine-learning algorithm that supplies the predictions. Furthermore, more accurate predictions tran…

Algebraic Dynamical Systems in Machine Learning
Iolo Jones, Jerry Swan, Jeffrey Giansiracusa
https://arXiv.org/abs/2311.03118 https://

Algebraic Dynamical Systems in Machine Learning
We introduce an algebraic analogue of dynamical systems, based on term rewriting. We show that a recursive function applied to the output of an iterated rewriting system defines a formal class of models into which all the main architectures for dynamic machine learning models (including recurrent neural networks, graph neural networks, and diffusion models) can be embedded. Considered in category theory, we also show that these algebraic models are a natural language for describing the composit…

I really like this scrolly visual explainer of generative AI terms like 'transformer', and it's a good overview of how machine learning models can understand your prompts and generate new sentences in response
https://ig.ft.com/generative-ai/

Generative AI exists because of the transformer
The technology has resulted in a host of cutting-edge AI applications — but its real power lies beyond text generation

Safety-Enhanced Self-Learning for Optimal Power Converter Control
Yihao Wan, Qianwen Xu, Tomislav Dragičević
https://arXiv.org/abs/2312.04158 https://

Safety-Enhanced Self-Learning for Optimal Power Converter Control
Data-driven learning-based control methods such as reinforcement learning (RL) have become increasingly popular with recent proliferation of the machine learning paradigm. These methods address the parameter sensitiveness and unmodeled dynamics in model-based controllers, such as finite control-set model predictive control. RL agents are typically utilized in simulation environments, where they are allowed to explore multiple "unsafe" actions during the learning process. However, this type of l…

A Markup examination of a typical college shows how students are subject to a vast and growing array of watchful tech, including homework trackers, test-taking software, and even license plate readers
https://themarkup.org/machine-learning

He Wanted Privacy. His College Gave Him None – The Markup
A Markup examination of a typical college shows how students are subject to a vast and growing array of watchful tech, including homework trackers, test-taking software, and even license plate readers

This https://arxiv.org/abs/2311.03133 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Enhancing generalizability of machine-learning turbulence models
Machine-learning (ML) models lack the generalizability exhibited by conventional empirical models. This limitation arises from the fact that ML models do not preserve the fundamental calibrations that make up a turbulent flow. Among these calibrations, the law of the wall (LoW) holds particular importance. This study aims to address this issue by incorporating LoW in existing machine-learning frameworks. If successful, this will significantly increase the generalizability of ML models. We focus…

This https://arxiv.org/abs/2310.00887 has been replaced.
Link: https://scholar.google.com/scholar?q=a

GRID: A Platform for General Robot Intelligence Development
Developing machine intelligence abilities in robots and autonomous systems is an expensive and time consuming process. Existing solutions are tailored to specific applications and are harder to generalize. Furthermore, scarcity of training data adds a layer of complexity in deploying deep machine learning models. We present a new platform for General Robot Intelligence Development (GRID) to address both of these issues. The platform enables robots to learn, compose and adapt skills to their phy…

Identification of Galaxy–Galaxy Strong #Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning: https://iopscience.iop.org/article/10.3847/1538-4357/ace4ba -> An international research collaboration trained computers to sift through millions of images for cosmic treasure: https://skyandtelescope.org/astronomy-news/astronomers-discover-562-new-candidate-strong-lenses-with-machine-learning/

IoT-Based Environmental Control System for Fish Farms with Sensor Integration and Machine Learning Decision Support
D. Dhinakaran, S. Gopalakrishnan, M.D. Manigandan, T. P. Anish
https://arXiv.org/abs/2311.04258

IoT-Based Environmental Control System for Fish Farms with Sensor Integration and Machine Learning Decision Support
In response to the burgeoning global demand for seafood and the challenges of managing fish farms, we introduce an innovative IoT based environmental control system that integrates sensor technology and advanced machine learning decision support. Deploying a network of wireless sensors within the fish farm, we continuously collect real-time data on crucial environmental parameters, including water temperature, pH levels, humidity, and fish behavior. This data undergoes meticulous preprocessing …

Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?
Walter Nelson, Jonathan Ranisau, Jeremy Petch
https://arXiv.org/abs/2311.05473

Do Ensembling and Meta-Learning Improve Outlier Detection in Randomized Controlled Trials?
Modern multi-centre randomized controlled trials (MCRCTs) collect massive amounts of tabular data, and are monitored intensively for irregularities by humans. We began by empirically evaluating 6 modern machine learning-based outlier detection algorithms on the task of identifying irregular data in 838 datasets from 7 real-world MCRCTs with a total of 77,001 patients from over 44 countries. Our results reinforce key findings from prior work in the outlier detection literature on data from other…

Green Party conference now looking at AI and the need for democratic regulation. Highlighting benefits as well as downsides. Very detailed motion.
Addendum: a (wrecking) motion to refer back, put by opponents of all AI/machine learning, was defeated.
#GreenParty #GPC23

Hydrogen diffusion in the lower mantle revealed by machine learning potentials
Yihang Peng, Jie Deng
https://arXiv.org/abs/2311.04461 https://

Hydrogen diffusion in the lower mantle revealed by machine learning potentials
Hydrogen may be incorporated into nominally anhydrous minerals including bridgmanite and post-perovskite as defects, making the Earth's deep mantle a potentially significant water reservoir. The diffusion of hydrogen and its contribution to the electrical conductivity in the lower mantle are rarely explored and remain largely unconstrained. Here we calculate hydrogen diffusivity in hydrous bridgmanite and post-perovskite, using molecular dynamics simulations driven by machine learning potential…

Machine learning of a density functional for anisotropic patchy particles
Alessandro Simon, Jens Weimar, Georg Martius, Martin Oettel
https://arXiv.org/abs/2311.04358

Machine learning of a density functional for anisotropic patchy particles
Anisotropic patchy particles have become an archetypical statistical model system for associating fluids. Here we formulate an approach to the Kern-Frenkel model via classical density functional theory to describe the positionally and orientationally resolved equilibrium density distributions in flat wall geometries. The density functional is split into a reference part for the orientationally averaged density and an orientational part in mean-field approximation. To bring the orientational par…

This https://arxiv.org/abs/2311.03755 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Multilingual Mathematical Autoformalization
Autoformalization is the task of translating natural language materials into machine-verifiable formalisations. Progress in autoformalization research is hindered by the lack of a sizeable dataset consisting of informal-formal pairs expressing the same essence. Existing methods tend to circumvent this challenge by manually curating small corpora or using few-shot learning with large language models. But these methods suffer from data scarcity and formal language acquisition difficulty. In this …

Thoughtful angle on the end of #Jezebel:
"... we have spent days or weeks on an in-depth investigation, published that investigation, been thanked by readers for shedding light on an issue they didn’t know about, been aggregated by our peers in the industry, & then have learned later that our article was deemed as unsuitable for programmatic advertising by a machine learning algorithm. This is the landscape that Jezebel & every other news outlet is playing in."
#media

This https://arxiv.org/abs/2201.00288 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Community Search: A Meta-Learning Approach
Community Search (CS) is one of the fundamental graph analysis tasks, which is a building block of various real applications. Given any query nodes, CS aims to find cohesive subgraphs that query nodes belong to. Recently, a large number of CS algorithms are designed. These algorithms adopt predefined subgraph patterns to model the communities, which cannot find ground-truth communities that do not have such pre-defined patterns in real-world graphs. Thereby, machine learning (ML) and deep learn…

Soundbay: Deep Learning Framework for Marine Mammals and Bioacoustic Research
Noam Bressler, Michael Faran, Amit Galor, Michael Moshe Michelashvili, Tomer Nachshon, Noa Weiss
https://arXiv.org/abs/2311.04343

Soundbay: Deep Learning Framework for Marine Mammals and Bioacoustic Research
This paper presents Soundbay, an open-source Python framework that allows bio-acoustics and machine learning researchers to implement and utilize deep learning-based algorithms for acoustic audio analysis. Soundbay provides an easy and intuitive platform for applying existing models on one's data or creating new models effortlessly. One of the main advantages of the framework is the capability to compare baselines on different benchmarks, a crucial part of emerging research and development rela…

This https://arxiv.org/abs/2309.00958 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Index-aware learning of circuits
Electrical circuits are present in a variety of technologies, making their design an important part of computer aided engineering. The growing number of tunable parameters that affect the final design leads to a need for new approaches of quantifying their impact. Machine learning may play a key role in this regard, however current approaches often make suboptimal use of existing knowledge about the system at hand. In terms of circuits, their description via modified nodal analysis is well-unde…

#Musicians are responding to #GenerativeAI in a binary way, no middle ground. Some adopt it, others reject it.
Essentially, it's Florence and the Machine Learning versus Rage Against the Machine Learning.
#AI

new study in Nature shows that bodily organs age at extraordinarily different rates, and each organ’s biological age can be at odds with a person’s age on paper:
“Organ aging signatures in the plasma proteome track health & disease”
https://www.nature.com/articles/s41586-023

Organ aging signatures in the plasma proteome track health and disease - Nature
Blood plasma protein data was combined with machine learning models for a simple method to determine differences in organ-specific aging; the study provides a basis for the prediction of diseases and aging effects using plasma proteomics.

The PetShop Dataset -- Finding Causes of Performance Issues across Microservices
Michaela Hardt, William Orchard, Patrick Blöbaum, Shiva Kasiviswanathan, Elke Kirschbaum
https://arXiv.org/abs/2311.04806

The PetShop Dataset -- Finding Causes of Performance Issues across Microservices
Identifying root causes for unexpected or undesirable behavior in complex systems is a prevalent challenge. This issue becomes especially crucial in modern cloud applications that employ numerous microservices. Although the machine learning and systems research communities have proposed various techniques to tackle this problem, there is currently a lack of standardized datasets for quantitative benchmarking. Consequently, research groups are compelled to create their own datasets for experimen…

Machine learning the drivers of carbon efficiency https://www.sciencedirect.com/science/article/abs/pii/S014098832300720X @…

"Machine learning & other types of AI are powerful statistical tools that have advanced almost every area of science by picking out patterns in data that are often invisible to human researchers. At the same time, some researchers worry that ill-informed use of #AI software is driving a deluge of papers with claims that cannot be replicated, or that are wrong or useless in practical terms.&quo…

This social Slack I'm on has a channel where we talk about advances in machine learning and it is called #aiaiai. Best name ever.

Forecasting Volatility with Machine Learning and Rough Volatility: Example from the Crypto-Winter
Siu Hin Tang, Mathieu Rosenbaum, Chao Zhou
https://arXiv.org/abs/2311.04727

Forecasting Volatility with Machine Learning and Rough Volatility: Example from the Crypto-Winter
We extend the application and test the performance of a recently introduced volatility prediction framework encompassing LSTM and rough volatility. Our asset class of interest is cryptocurrencies, at the beginning of the "crypto-winter" in 2022. We first show that to forecast volatility, a universal LSTM approach trained on a pool of assets outperforms traditional models. We then consider a parsimonious parametric model based on rough volatility and Zumbach effect. We obtain similar prediction …

Machine learning techniques to distinguish near-field interference and far-field astrophysical signals in radio telescopes
K. J. Luke
https://arXiv.org/abs/2311.04868

Machine learning techniques to distinguish near-field interference and far-field astrophysical signals in radio telescopes
The CHIME radio telescope operates in the frequency bandwidth of 400 to 800 MHz. The CHIME/FRB collaboration has a data pipeline that analyzes the data in real time, suppresses radio frequency interferences (RFI) and searches for FRBs. However, the RFI removal techniques work best for broadband and narrow FRBs.We wish to create a RFI removal technique that works without making assumptions about the characteristics of the FRB signal. In this thesis we first explore the data of intensity generate…

The Use of Quantitative Metrics and Machine Learning to Predict Radiologist Interpretations of MRI Image Quality and Artifacts
Lucas McCullum, John Wood, Maria Gule-Monroe, Ho-Ling Anthony Liu, Melissa Chen, Komal Shah, Noah Nathan Chasen, Vinodh Kumar, Ping Hou, Jason Stafford, Caroline Chung, Moiz Ahmad, Christopher Walker, Joshua Yung
https://

The Use of Quantitative Metrics and Machine Learning to Predict Radiologist Interpretations of MRI Image Quality and Artifacts
A dataset of 3D-GRE and 3D-TSE brain 3T post contrast T1-weighted images as part of a quality improvement project were collected and shown to five neuro-radiologists who evaluated each sequence for both image quality and imaging artifacts. The same scans were processed using the MRQy tool for objective, quantitative image quality metrics. Using the combined radiologist and quantitative metrics dataset, a decision tree classifier with a bagging ensemble approach was trained to predict radiologis…

This https://arxiv.org/abs/2210.09275 has been replaced.
Link: https://scholar.google.com/scholar?q=a

This https://arxiv.org/abs/2205.05628 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification
With the increasing prevalence of encrypted network traffic, cyber security analysts have been turning to machine learning (ML) techniques to elucidate the traffic on their networks. However, ML models can become stale as new traffic emerges that is outside of the distribution of the training set. In order to reliably adapt in this dynamic environment, ML models must additionally provide contextualized uncertainty quantification to their predictions, which has received little attention in the c…

Just-in-time Quantization with Processing-In-Memory for Efficient ML Training
Mohamed Assem Ibrahim, Shaizeen Aga, Ada Li, Suchita Pati, Mahzabeen Islam
https://arXiv.org/abs/2311.05034

Just-in-time Quantization with Processing-In-Memory for Efficient ML Training
Data format innovations have been critical for machine learning (ML) scaling, which in turn fuels ground-breaking ML capabilities. However, even in the presence of low-precision formats, model weights are often stored in both high-precision and low-precision during training. Furthermore, with emerging directional data formats (e.g., MX9, MX6, etc.) multiple low-precision weight copies can be required. To lower memory capacity needs of weights, we explore just-in-time quantization (JIT-Q) where …

This https://arxiv.org/abs/2310.03334 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System
Network Intrusion Detection System (NIDS) is a key component in securing the computer network from various cyber security threats and network attacks. However, consider an unfortunate situation where the NIDS is itself attacked and vulnerable more specifically, we can say, How to defend the defender?. In Adversarial Machine Learning (AML), the malicious actors aim to fool the Machine Learning (ML) and Deep Learning (DL) models to produce incorrect predictions with intentionally crafted adversar…

"Why Experiment: Machine Learning at the Library of Congress" https://blogs.loc.gov/thesignal/2023/11/why-experiment-machine-learning-at-the-library-of-congress/

Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data
Feifei Wang, Huiyun Tang, Yang Li
https://arXiv.org/abs/2312.04281

Factor-Assisted Federated Learning for Personalized Optimization with Heterogeneous Data
Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data heterogeneity is one of the core challenges in federated learning, which could severely degrade the convergence rate and prediction performance of deep neural networks. To address this issue, we develop a novel personalized federated learning framework for heterogeneous data, which we refer to as FedSplit. This modeling framework is motivated by the finding that, data in different cl…

This https://arxiv.org/abs/2209.07863 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Expanding continual few-shot learning benchmarks to include recognition of specific instances
Continual learning and few-shot learning are important frontiers in progress towards broader Machine Learning (ML) capabilities. There is a growing body of work in both, but few works combining the two. One exception is the Continual few-shot Learning (CFSL) framework of Antoniou et al. arXiv:2004.11967. In this study, we extend CFSL in two ways that capture a broader range of challenges, important for intelligent agent behaviour in real-world conditions. First, we modify CFSL to make it more c…

This https://arxiv.org/abs/2211.03963 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Fast Algorithms for $\ell_p$-Regression
The $\ell_p$-norm regression problem is a classic problem in optimization with wide ranging applications in machine learning and theoretical computer science. The goal is to compute $x^{\star} =\arg\min_{Ax=b}\|x\|_p^p$, where $x^{\star}\in \mathbb{R}^n, A\in \mathbb{R}^{d\times n},b \in \mathbb{R}^d$ and $d\leq n$. Efficient high-accuracy algorithms for the problem have been challenging both in theory and practice and the state of the art algorithms require $poly(p)\cdot n^{\frac{1}{…

The impact of recent developments in AI on cultural heritage research was the topic of my presentation yesterday at the IM/MATERIALITIES - Museums between Real and Digital conference entitled "The Ghost of the Machine - AIs Impact on Cultural Heritage Research"
Presentation Slides: https://zenodo.org/records/10244628

A Review and Taxonomy of Methods for Quantifying Dataset Similarity
Marieke Stolte, Andrea Bommert, Jörg Rahnenführer
https://arXiv.org/abs/2312.04078 http…

A Review and Taxonomy of Methods for Quantifying Dataset Similarity
In statistics and machine learning, measuring the similarity between two or more datasets is important for several purposes. The performance of a predictive model on novel datasets, referred to as generalizability, critically depends on how similar the dataset used for fitting the model is to the novel datasets. Exploiting or transferring insights between similar datasets is a key aspect of meta-learning and transfer-learning. In two-sample testing, it is checked, whether the underlying (multiv…

A Markup examination of a typical college shows how students are subject to a vast and growing array of watchful tech, including homework trackers, test-taking software, and even license plate readers
https://themarkup.org/machine-learning

He Wanted Privacy. His College Gave Him None – The Markup
A Markup examination of a typical college shows how students are subject to a vast and growing array of watchful tech, including homework trackers, test-taking software, and even license plate readers

'A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle' http://arxiv.org/abs/1901.10002 lists 7 potential sources of harm in machine learning: historical, representation, measurement, aggregation, learning, evaluation and deployment biases

A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
As machine learning (ML) increasingly affects people and society, awareness of its potential unwanted consequences has also grown. To anticipate, prevent, and mitigate undesirable downstream consequences, it is critical that we understand when and how harm might be introduced throughout the ML life cycle. In this paper, we provide a framework that identifies seven distinct potential sources of downstream harm in machine learning, spanning data collection, development, and deployment. In doing s…

This https://arxiv.org/abs/2311.03133 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Enhancing generalizability of machine-learning turbulence models
Machine-learning (ML) models lack the generalizability exhibited by conventional empirical models. This limitation arises from the fact that ML models do not preserve the fundamental calibrations that make up a turbulent flow. Among these calibrations, the law of the wall (LoW) holds particular importance. This study aims to address this issue by incorporating LoW in existing machine-learning frameworks. If successful, this will significantly increase the generalizability of ML models. We focus…

This https://arxiv.org/abs/2307.04052 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Learning to Group Auxiliary Datasets for Molecule
The limited availability of annotations in small molecule datasets presents a challenge to machine learning models. To address this, one common strategy is to collaborate with additional auxiliary datasets. However, having more data does not always guarantee improvements. Negative transfer can occur when the knowledge in the target dataset differs or contradicts that of the auxiliary molecule datasets. In light of this, identifying the auxiliary molecule datasets that can benefit the target dat…

This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective. We show that DMs can be conceptualized by reversing a stochastic process driven by the Langevin equation, which then produces samples from an initial distribution to approximate the target distribution. In a toy model, we highlight the capability of DMs to learn effective actions. Furthermore, we demonstrate its feasibility to act as a global sampler for generating configurations in the two-dimensional $\phi^4$ quantum lattice field theory.
[https://arxiv.org/abs/2311.03578v1]

Soundbay: Deep Learning Framework for Marine Mammals and Bioacoustic Research
Noam Bressler, Michael Faran, Amit Galor, Michael Moshe Michelashvili, Tomer Nachshon, Noa Weiss
https://arXiv.org/abs/2311.04343

Soundbay: Deep Learning Framework for Marine Mammals and Bioacoustic Research
This paper presents Soundbay, an open-source Python framework that allows bio-acoustics and machine learning researchers to implement and utilize deep learning-based algorithms for acoustic audio analysis. Soundbay provides an easy and intuitive platform for applying existing models on one's data or creating new models effortlessly. One of the main advantages of the framework is the capability to compare baselines on different benchmarks, a crucial part of emerging research and development rela…

This https://arxiv.org/abs/2205.08821 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Lessons Learned: Defending Against Property Inference Attacks
This work investigates and evaluates multiple defense strategies against property inference attacks (PIAs), a privacy attack against machine learning models. Given a trained machine learning model, PIAs aim to extract statistical properties of its underlying training data, e.g., reveal the ratio of men and women in a medical training data set. While for other privacy attacks like membership inference, a lot of research on defense mechanisms has been published, this is the first work focusing on…

How a California college is employing data collection tools to track students' daily movements, including e-proctoring software and license plate readers (Tara García Mathewson/The Markup)
https://themarkup.org/machine-learning/202…

He Wanted Privacy. His College Gave Him None – The Markup
A Markup examination of a typical college shows how students are subject to a vast and growing array of watchful tech, including homework trackers, test-taking software, and even license plate readers

This https://arxiv.org/abs/2304.07143 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

A Review on Car-Following Model
The car-following (CF) model is the core component for traffic simulations and has been built-in in many production vehicles with Advanced Driving Assistance Systems (ADAS). Research of CF behavior allows us to identify the sources of different macro phenomena induced by the basic process of pairwise vehicle interaction. The CF behavior and control model encompasses various fields, such as traffic engineering, physics, cognitive science, machine learning, and reinforcement learning. This paper …

"Machine learning & other types of AI are powerful statistical tools that have advanced almost every area of science by picking out patterns in data that are often invisible to human researchers. At the same time, some researchers worry that ill-informed use of #AI software is driving a deluge of papers with claims that cannot be replicated, or that are wrong or useless in practical terms.&quo…

The Sample Complexity Of ERMs In Stochastic Convex Optimization
Daniel Carmon, Roi Livni, Amir Yehudayoff
https://arXiv.org/abs/2311.05398 https://<…

The Sample Complexity Of ERMs In Stochastic Convex Optimization
Stochastic convex optimization is one of the most well-studied models for learning in modern machine learning. Nevertheless, a central fundamental question in this setup remained unresolved: "How many data points must be observed so that any empirical risk minimizer (ERM) shows good performance on the true population?" This question was proposed by Feldman (2016), who proved that $Ω(\frac{d}ε+\frac{1}{ε^2})$ data points are necessary (where $d$ is the dimension and $ε>0$ is the accuracy par…

Airfoil generation and feature extraction using the conditional VAE-WGAN-gp
Kazuo Yonekura, Yuki Tomori, Katsuyuki Suzuki
https://arXiv.org/abs/2311.05445 …

Airfoil generation and feature extraction using the conditional VAE-WGAN-gp
A machine learning method was applied to solve an inverse airfoil design problem. A conditional VAE-WGAN-gp model, which couples the conditional variational autoencoder (VAE) and Wasserstein generative adversarial network with gradient penalty (WGAN-gp), is proposed for an airfoil generation method, and then it is compared with the WGAN-gp and VAE models. The VAEGAN model couples the VAE and GAN models, which enables feature extraction in the GAN models. In airfoil generation tasks, to generate…

This https://arxiv.org/abs/2310.04414 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
Analyzing model performance in various unseen environments is a critical research problem in the machine learning community. To study this problem, it is important to construct a testbed with out-of-distribution test sets that have broad coverage of environmental discrepancies. However, existing testbeds typically either have a small number of domains or are synthesized by image corruptions, hindering algorithm design that demonstrates real-world effectiveness. In this paper, we introduce CIFAR…

Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs
Hongwu Peng, Caiwen Ding, Tong Geng, Sutanay Choudhury, Kevin Barker, Ang Li
https://arXiv.org/abs/2311.04417

Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs
The relentless advancement of artificial intelligence (AI) and machine learning (ML) applications necessitates the development of specialized hardware accelerators capable of handling the increasing complexity and computational demands. Traditional computing architectures, based on the von Neumann model, are being outstripped by the requirements of contemporary AI/ML algorithms, leading to a surge in the creation of accelerators like the Graphcore Intelligence Processing Unit (IPU), Sambanova R…

This https://arxiv.org/abs/2310.00498 has been replaced.
Link: https://scholar.google.com/scholar?q=a

Automated Gait Generation For Walking, Soft Robotic Quadrupeds
Gait generation for soft robots is challenging due to the nonlinear dynamics and high dimensional input spaces of soft actuators. Limitations in soft robotic control and perception force researchers to hand-craft open loop controllers for gait sequences, which is a non-trivial process. Moreover, short soft actuator lifespans and natural variations in actuator behavior limit machine learning techniques to settings that can be learned on the same time scales as robot deployment. Lastly, simulatio…

Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures
Michael Kölle, Jonas Maurer, Philipp Altmann, Leo Sünkel, Jonas Stein, Claudia Linnhoff-Popien
https://arXiv.org/abs/2311.05559

Understanding emotions in the context of IT-based self-monitoring
Danielly de Paula, Florian Borchert, Ariane Sasso, Falk Uebernickel
https://arXiv.org/abs/2311.05449

Understanding emotions in the context of IT-based self-monitoring
This study explores the intersection of information technology-based self-monitoring (ITSM) and emotional responses in chronic care. It critiques the lack of theoretical depth in current ITSM research and proposes a dynamic emotion process theory to understand ITSM's impact on users' emotions. Utilizing computational grounded theory and machine learning analysis of hypertension app reviews, the research seeks to extend emotion theory by examining ITSM stimuli and their influence on emotional ep…

GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
Ziqi Li
https://arXiv.org/abs/2312.03675 https://

GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
This paper introduces GeoShapley, a game theory approach to measuring spatial effects in machine learning models. GeoShapley extends the Nobel Prize-winning Shapley value framework in game theory by conceptualizing location as a player in a model prediction game, which enables the quantification of the importance of location and the synergies between location and other features in a model. GeoShapley is a model-agnostic approach and can be applied to statistical or black-box machine learning mo…

[2023-11-10 Fri (UTC), 4 new articles found for stat.ML Machine Learning]

GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
Ziqi Li
https://arXiv.org/abs/2312.03675 https://

GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models
This paper introduces GeoShapley, a game theory approach to measuring spatial effects in machine learning models. GeoShapley extends the Nobel Prize-winning Shapley value framework in game theory by conceptualizing location as a player in a model prediction game, which enables the quantification of the importance of location and the synergies between location and other features in a model. GeoShapley is a model-agnostic approach and can be applied to statistical or black-box machine learning mo…

This https://arxiv.org/abs/2303.05488 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Optimizing quantum noise-induced reservoir computing for nonlinear and chaotic time series prediction
Quantum reservoir computing is strongly emerging for sequential and time series data prediction in quantum machine learning. We make advancements to the quantum noise-induced reservoir, in which reservoir noise is used as a resource to generate expressive, nonlinear signals that are efficiently learned with a single linear output layer. We address the need for quantum reservoir tuning with a novel and generally applicable approach to quantum circuit parameterization, in which tunable noise mode…

Toward Rapid, Optimal, and Feasible Power Dispatch through Generalized Neural Mapping
Meiyi Li, Javad Mohammadi
https://arXiv.org/abs/2311.04838 https://…

Toward Rapid, Optimal, and Feasible Power Dispatch through Generalized Neural Mapping
The evolution towards a more distributed and interconnected grid necessitates large-scale decision-making within strict temporal constraints. Machine learning (ML) paradigms have demonstrated significant potential in improving the efficacy of optimization processes. However, the feasibility of solutions derived from ML models continues to pose challenges. It's imperative that ML models produce solutions that are attainable and realistic within the given system constraints of power systems. To a…

GLAM / @… folk, would this approach be useful / interesting with CHI collections?
'Large sets of diverse data present several challenges for clustering, but through a novel approach that combines dimensionality reduction, recursion, and supervised machine learning, we’ve been able to obtain strong results. Using part of the algorithm, we’re able to obtain a greater understan…

Recursive Embedding and Clustering - Spotify Engineering
Recursive Embedding and Clustering - Spotify Engineering

A Survey on Radar-Based Fall Detection
Shuting Hu, Siyang Cao, Nima Toosizadeh, Jennifer Barton, Melvin G. Hector, Mindy J. Fain
https://arXiv.org/abs/2312.04037

A Survey on Radar-Based Fall Detection
Fall detection, particularly critical for high-risk demographics like the elderly, is a key public health concern where timely detection can greatly minimize harm. With the advancements in radio frequency technology, radar has emerged as a powerful tool for human detection and tracking. Traditional machine learning algorithms, such as Support Vector Machines (SVM) and k-Nearest Neighbors (kNN), have shown promising outcomes. However, deep learning approaches, notably Convolutional Neural Networ…

Coherent energy and force uncertainty in deep learning force fields
Peter BjŸrn JŸrgensen, Jonas Busk, Ole Winther, Mikkel N. Schmidt
https://arXiv.org/abs/2312.04174

Coherent energy and force uncertainty in deep learning force fields
In machine learning energy potentials for atomic systems, forces are commonly obtained as the negative derivative of the energy function with respect to atomic positions. To quantify aleatoric uncertainty in the predicted energies, a widely used modeling approach involves predicting both a mean and variance for each energy value. However, this model is not differentiable under the usual white noise assumption, so energy uncertainty does not naturally translate to force uncertainty. In this work…

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System
Xinwei Yuan, Shu Han, Wei Huang, Hongliang Ye, Xianglong Kong, Fan Zhang
https://arXiv.org/abs/2312.03245

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System
Deep learning based intrusion detection systems (DL-based IDS) have emerged as one of the best choices for providing security solutions against various network intrusion attacks. However, due to the emergence and development of adversarial deep learning technologies, it becomes challenging for the adoption of DL models into IDS. In this paper, we propose a novel IDS architecture that can enhance the robustness of IDS against adversarial attacks by combining conventional machine learning (ML) mo…

Counterfactually Fair Representation
Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang
https://arXiv.org/abs/2311.05420 https://arXiv.o…

Counterfactually Fair Representation
The use of machine learning models in high-stake applications (e.g., healthcare, lending, college admission) has raised growing concerns due to potential biases against protected social groups. Various fairness notions and methods have been proposed to mitigate such biases. In this work, we focus on Counterfactual Fairness (CF), a fairness notion that is dependent on an underlying causal graph and first proposed by Kusner \textit{et al.}~\cite{kusner2017counterfactual}; it requires that the out…

This https://arxiv.org/abs/2309.06240 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivity
Reliable uncertainty quantification (UQ) in machine learning (ML) regression tasks is becoming the focus of many studies in materials and chemical science. It is now well understood that average calibration is insufficient, and most studies implement additional methods testing the conditional calibration with respect to uncertainty, i.e. consistency. Consistency is assessed mostly by so-called reliability diagrams. There exists however another way beyond average calibration, which is conditiona…

This https://arxiv.org/abs/2310.04292 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the bound…

This https://arxiv.org/abs/2303.01679 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Automated Machine Learning for Deep Learning based Malware Detection
Deep learning (DL) has proven to be effective in detecting sophisticated malware that is constantly evolving. Even though deep learning has alleviated the feature engineering problem, finding the most optimal DL model, in terms of neural architecture search (NAS) and the model's optimal set of hyper-parameters, remains a challenge that requires domain expertise. In addition, many of the proposed state-of-the-art models are very complex and may not be the best fit for different datasets. A promi…

This https://arxiv.org/abs/2310.11891 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

A Hyperparameter Study for Quantum Kernel Methods
Quantum kernel methods are a promising method in quantum machine learning thanks to the guarantees connected to them. Their accessibility for analytic considerations also opens up the possibility of prescreening datasets based on their potential for a quantum advantage. To do so, earlier works developed the geometric difference, which can be understood as a closeness measure between two kernel-based machine learning approaches, most importantly between a quantum kernel and classical kernel. Thi…

Parkinson's Disease Detection through Vocal Biomarkers and Advanced Machine Learning Algorithms: A Comprehensive Study
Md Abu Sayed, Sabbir Ahamed, Duc M Cao, Md Eyasin Ul Islam Pavel, Malay Sarkar, Md Tuhin Mia
https://arXiv.org/abs/2311.05435

This https://arxiv.org/abs/2310.14662 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Estimation of forest height and biomass from open-access multi-sensor satellite imagery and GEDI Lidar data: high-resolution maps of metropolitan France
Mapping forest resources and carbon is important for improving forest management and meeting the objectives of storing carbon and preserving the environment. Spaceborne remote sensing approaches have considerable potential to support forest height monitoring by providing repeated observations at high spatial resolution over large areas. This study uses a machine learning approach that was previously developed to produce local maps of forest parameters (basal area, height, diameter, etc.). The a…

This https://arxiv.org/abs/2307.00908 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Quantum Machine Learning on Near-Term Quantum Devices: Current State of Supervised and Unsupervised Techniques for Real-World Applications
The past decade has witnessed significant advancements in quantum hardware, encompassing improvements in speed, qubit quantity, and quantum volume-a metric defining the maximum size of a quantum circuit effectively implementable on near-term quantum devices. This progress has led to a surge in Quantum Machine Learning (QML) applications on real hardware, aiming to achieve quantum advantage over classical approaches. This survey focuses on selected supervised and unsupervised learning applicatio…

This https://arxiv.org/abs/2305.15092 has been replaced.
Link: https://scholar.google.com/scholar?q=a

FedZero: Leveraging Renewable Excess Energy in Federated Learning
Federated Learning (FL) is an emerging machine learning technique that enables distributed model training across data silos or edge devices without data sharing. Yet, FL inevitably introduces inefficiencies compared to centralized model training, which will further increase the already high energy usage and associated carbon emissions of machine learning in the future. One idea to reduce FL's carbon footprint is to schedule training jobs based on the availability of renewable excess energy that…

Reconsideration on evaluation of machine learning models in continuous monitoring using wearables
Cheng Ding, Zhicheng Guo, Cynthia Rudin, Ran Xiao, Fadi B Nahab, Xiao Hu
https://arXiv.org/abs/2312.02300

Reconsideration on evaluation of machine learning models in continuous monitoring using wearables
This paper explores the challenges in evaluating machine learning (ML) models for continuous health monitoring using wearable devices beyond conventional metrics. We state the complexities posed by real-world variability, disease dynamics, user-specific characteristics, and the prevalence of false notifications, necessitating novel evaluation strategies. Drawing insights from large-scale heart studies, the paper offers a comprehensive guideline for robust ML model evaluation on continuous healt…

This https://arxiv.org/abs/2310.00077 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Additive Manufacturing
Zhangyue Shi, Tianxin Xie, Chenang Liu, Yuxuan Li
https://arXiv.org/abs/2312.02491

Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Additive Manufacturing
The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven in-situ quality monitoring based on the sensor data collected in manufacturing processes. However, one critical challenge is that newly presented defect category may manifest as the manufacturing process continues, resulting in monitoring performance deterioration of previously trained machine learning models. Hence, there is an increasing need for empowering…

Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Additive Manufacturing
Zhangyue Shi, Tianxin Xie, Chenang Liu, Yuxuan Li
https://arXiv.org/abs/2312.02491

Pseudo Replay-based Class Continual Learning for Online New Category Anomaly Detection in Additive Manufacturing
The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven in-situ quality monitoring based on the sensor data collected in manufacturing processes. However, one critical challenge is that newly presented defect category may manifest as the manufacturing process continues, resulting in monitoring performance deterioration of previously trained machine learning models. Hence, there is an increasing need for empowering…

AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design
Romain Lacombe, Lucas Hendren, Khalid El-Awady
https://arXiv.org/abs/2312.02308

AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design
A central challenge of the clean energy transition is the development of catalysts for low-emissions technologies. Recent advances in Machine Learning for quantum chemistry drastically accelerate the computation of catalytic activity descriptors such as adsorption energies. Here we introduce AdsorbRL, a Deep Reinforcement Learning agent aiming to identify potential catalysts given a multi-objective binding energy target, trained using offline learning on the Open Catalyst 2020 and Materials Pro…

Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciar\'an
Andrew J. Charlton-Perez, Helen F. Dacre, Simon Driscoll, Suzanne L. Gray, Ben Harvey, Natalie J. Harvey, Kieran M. R. Hunt, Robert W. Lee, Ranjini Swaminathan, Remy Vandaele, Ambrogio Volonté
https://

Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán
There has been huge recent interest in the potential of making operational weather forecasts using machine learning techniques. As they become a part of the weather forecasting toolbox, there is a pressing need to understand how well current machine learning models can simulate high-impactweather events. We compare forecasts of Storm Ciarán, a European windstorm that caused sixteen deaths and extensive damage in Northern Europe, made by machine learning and numericalweather prediction models. …

This https://arxiv.org/abs/2310.02164 has been replaced.
Link: https://scholar.google.com/scholar?q=a

A Survey of Graph Unlearning
Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the right to be forgotten. It is evident that graph machine learning exhibits sensitivity to data privacy and adversarial attacks, necessitating the application of graph unlearning techniques to address these concerns effectively. In this comprehensive survey paper, we present the first systematic review of graph unlearnin…

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
Weitao Du, Jiujiu Chen, Xuecang Zhang, Zhiming Ma, Shengchao Liu
https://arXiv.org/abs/2312.03475

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
Recently, artificial intelligence for drug discovery has raised increasing interest in both machine learning and chemistry domains. The fundamental building block for drug discovery is molecule geometry and thus, the molecule's geometrical representation is the main bottleneck to better utilize machine learning techniques for drug discovery. In this work, we propose a pretraining method for molecule joint auto-encoding (MoleculeJAE). MoleculeJAE can learn both the 2D bond (topology) and 3D conf…

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
Weitao Du, Jiujiu Chen, Xuecang Zhang, Zhiming Ma, Shengchao Liu
https://arXiv.org/abs/2312.03475

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
Recently, artificial intelligence for drug discovery has raised increasing interest in both machine learning and chemistry domains. The fundamental building block for drug discovery is molecule geometry and thus, the molecule's geometrical representation is the main bottleneck to better utilize machine learning techniques for drug discovery. In this work, we propose a pretraining method for molecule joint auto-encoding (MoleculeJAE). MoleculeJAE can learn both the 2D bond (topology) and 3D conf…

Expressive Sign Equivariant Networks for Spectral Geometric Learning
Derek Lim, Joshua Robinson, Stefanie Jegelka, Haggai Maron
https://arXiv.org/abs/2312.02339

Expressive Sign Equivariant Networks for Spectral Geometric Learning
Recent work has shown the utility of developing machine learning models that respect the structure and symmetries of eigenvectors. These works promote sign invariance, since for any eigenvector v the negation -v is also an eigenvector. However, we show that sign invariance is theoretically limited for tasks such as building orthogonally equivariant models and learning node positional encodings for link prediction in graphs. In this work, we demonstrate the benefits of sign equivariance for thes…