A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study shows dataset properties impact adversarial machine learning robustness.
Deep models generate geometric objects with global properties.
Study links different drug property prediction methods and datasets.
Multi-party machine learning leaks global dataset properties even with black-box access.
Study on protecting sensitive properties of datasets during analysis.
Meta-learning symbolic default hyperparameters from dataset properties.
Paper introduces attacks to infer GAN training dataset properties.
A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders with arbitrary manifolds as a latent space. A Diffusion Variational Autoencoder uses t…
Paper improves molecular property prediction using denoising autoencoders.
This paper analyzes how data and model properties affect membership inference attacks.
New dataset DFT for drug-like molecules benchmarks neural network potentials.
Hölder-DPO aligns models robustly with noisy human feedback.
FlowMO uses Gaussian Processes for molecular property prediction with uncertainty.
The paper discusses regularization properties of artificial data for deep learning. Artificial datasets allow to train neural networks in the case of a real data shortage. It is demonstrated that the artificial data generation process, described as injecting noise to high-level features, bears several similarities to e…
This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifical…
This paper creates a comprehensive BTC transaction network dataset spanning 15 years.
Study explores calibration properties in neural architectures.
PropEn uses matching to create a larger dataset for efficient design optimization.
Partial Wasserstein Covering aims to identify missing patterns in datasets.
Study shows explanation disparities in machine learning models are influenced by data and model properties.
New benchmarks for offline RL from diverse datasets.
We introduce the Hierarchically Interacting Particle Neural Network (HIP-NN) to model molecular properties from datasets of quantum calculations. Inspired by a many-body expansion, HIP-NN decomposes properties, such as energy, as a sum over hierarchical terms. These terms are generated from a neural network--a composit…
The practical success of widely used machine learning (ML) and deep learning (DL) algorithms in Artificial Intelligence (AI) community owes to availability of large datasets for training and huge computational resources. Despite the enormous practical success of AI, these algorithms are only loosely inspired from the b…
We present a novel condition, which we term the net- work nullspace property, which ensures accurate recovery of graph signals representing massive network-structured datasets from few signal values. The network nullspace property couples the cluster structure of the underlying network-structure with the geometry of th…
One significant challenge to scaling entity resolution algorithms to massive datasets is understanding how performance changes after moving beyond the realm of small, manually labeled reference datasets. Unlike traditional machine learning tasks, when an entity resolution algorithm performs well on small hold-out datas…
Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing p…
We introduce a new parameter to measure the inhomogeneity of training datasets.
The PAC-Bayesian approach is a powerful set of techniques to derive non- asymptotic risk bounds for random estimators. The corresponding optimal distribution of estimators, usually called the Gibbs posterior, is unfortunately intractable. One may sample from it using Markov chain Monte Carlo, but this is often too slow…
Five simple soft sensor methodologies with two update conditions were compared on two experimentally-obtained datasets and one simulated dataset. The soft sensors investigated were moving window partial least squares regression (and a recursive variant), moving window random forest regression, the mean moving window of…
CHILI datasets tackle inorganic nanomaterials, advancing graph machine learning.
TimeGraph creates synthetic datasets for robust time-series causal discovery.
New online feature selection method handles streaming data with concept drift.
The paper explores how neural networks generalize differently from natural and medical images.
One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance of a GAN by comparing geometrical properties of the underlying data manifold and …
METASET selects diverse unit cells for efficient data-driven metamaterial design.
Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials. In this work we extend the neural message passing model with an edge update network which allows the information exchanged between atoms to depend on the hidde…
Evaluation of hydrocarbon reservoir requires classification of petrophysical properties from available dataset. However, characterization of reservoir attributes is difficult due to the nonlinear and heterogeneous nature of the subsurface physical properties. In this context, present study proposes a generalized one cl…
With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry, data is inherently small and fragmented. In this work, we develop an approach of using rule-based knowledge for training ChemNet, a transferable and generalizable de…
Large learning rates enhance model robustness and compressibility.
Wiki-CS dataset benchmarks Graph Neural Networks using Wikipedia articles.
We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules w…
Enhances scenario approach for certifying design properties post-design.
RIn-Close_CVC is an efficient (take polynomial time per bicluster), complete (find all maximal biclusters), correct (all biclusters attend the user-defined level of consistency) and non-redundant (all the obtained biclusters are maximal and the same bicluster is not enumerated more than once) enumerative algorithm for …
CNP improves few-shot learning for docking scores in molecular datasets.
We propose improving the privacy properties of a dataset by publishing only a strategically chosen "core-set" of the data containing a subset of the instances. The core-set allows strong performance on primary tasks, but forces poor performance on unwanted tasks. We give methods for both linear models and neural networ…
Prediction of molecular properties, including physico-chemical properties, is a challenging task in chemistry. Herein we present a new state-of-the-art multitask prediction method based on existing graph neural network models. We have used different architectures for our models and the results clearly demonstrate that …
Machine-learning models are capable of capturing the structure-property relationship from a dataset of computationally demanding ab initio calculations. Over the past two years, the Organic Materials Database (OMDB) has hosted a growing number of calculated electronic properties of previously synthesized organic crysta…
We propose Cormorant, a rotationally covariant neural network architecture for learning the behavior and properties of complex many-body physical systems. We apply these networks to molecular systems with two goals: learning atomic potential energy surfaces for use in Molecular Dynamics simulations, and learning ground…