English
Related papers

Related papers: Do we need equivariant models for molecule generat…

200 papers

Research into deep learning models for molecular property prediction has primarily focused on the development of better Graph Neural Network (GNN) architectures. Though new GNN variants continue to improve performance, their modifications…

Quantitative Methods · Quantitative Biology 2021-11-23 Toni Sagayaraj , Carsten Eickhoff

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

Discrete graph generation has emerged as a powerful paradigm for modeling graph data, often relying on highly expressive neural backbones such as transformers or higher-order architectures. We revisit this design choice by introducing…

Machine Learning · Computer Science 2026-03-11 Jay Revolinsky , Harry Shomer , Jiliang Tang

Content and image generation consist in creating or generating data from noisy information by extracting specific features such as texture, edges, and other thin image structures. We are interested here in generative models, and two main…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 El Hadji S. Diop , Thierno Fall , Alioune Mbengue , Mohamed Daoudi

Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Zifan Shi , Sida Peng , Yinghao Xu , Andreas Geiger , Yiyi Liao , Yujun Shen

We consider the conditional generation of 3D drug-like molecules with \textit{explicit control} over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikeness or Synthetic Accessibility score) and…

Machine Learning · Computer Science 2024-12-20 Haoran Liu , Youzhi Luo , Tianxiao Li , James Caverlee , Martin Renqiang Min

Geometric graph neural networks (GNNs) that respect E(3) symmetries have achieved strong performance on small molecule modeling, but they face scalability and expressiveness challenges when applied to large biomolecules such as RNA and…

Biomolecules · Quantitative Biology 2025-06-26 Junjie Xu , Jiahao Zhang , Mangal Prakash , Xiang Zhang , Suhang Wang

Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories. Thanks to their fast inference times they promise…

When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…

Geophysics · Physics 2021-04-28 Jorge Lopez-Alvis , Eric Laloy , Frédéric Nguyen , Thomas Hermans

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in…

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such…

Machine Learning · Computer Science 2020-06-22 Luca Franceschi , Mathias Niepert , Massimiliano Pontil , Xiao He

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Machine Learning · Computer Science 2017-08-22 Luke Taylor , Geoff Nitschke

Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has…

Machine Learning · Computer Science 2021-11-02 Tetsu Kasanishi , Xueting Wang , Toshihiko Yamasaki

In many machine learning tasks it is desirable that a model's prediction transforms in an equivariant way under transformations of its input. Convolutional neural networks (CNNs) implement translational equivariance by construction; for…

Machine Learning · Computer Science 2018-03-20 Maurice Weiler , Fred A. Hamprecht , Martin Storath

Cross-modality image estimation involves the generation of images of one medical imaging modality from that of another modality. Convolutional neural networks (CNNs) have been shown to be useful in identifying, characterising and extracting…

Image and Video Processing · Electrical Eng. & Systems 2021-06-07 Azin Shokraei Fard , David C. Reutens , Viktor Vegh

The goal of structure-based drug discovery is to find small molecules that bind to a given target protein. Deep learning has been used to generate drug-like molecules with certain cheminformatic properties, but has not yet been applied to…

Quantitative Methods · Quantitative Biology 2022-01-27 Matthew Ragoza , Tomohide Masuda , David Ryan Koes

We propose a novel class of neural network-like parametrized functions, i.e., general transformation neural networks (GTNNs), for high-dimensional approximation. Conventional deep neural networks sometimes perform less accurately on…

Numerical Analysis · Mathematics 2026-02-25 Xiaoyang Wang , Yiqi Gu

Generating molecular graphs is a challenging task due to their discrete nature and the competitive objectives involved. Diffusion models have emerged as SOTA approaches in data generation across various modalities. For molecular graphs,…

Machine Learning · Computer Science 2025-01-08 Prashanth Pombala , Gerrit Grossmann , Verena Wolf

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due…

Machine Learning · Computer Science 2018-06-26 Jiaxuan You , Rex Ying , Xiang Ren , William L. Hamilton , Jure Leskovec

The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in…

Machine Learning · Statistics 2018-05-29 Gia-Lac Tran , Edwin V. Bonilla , John P. Cunningham , Pietro Michiardi , Maurizio Filippone