English
Related papers

Related papers: Geometric and Physical Quantities Improve E(3) Equ…

200 papers

Message-passing neural networks (MPNNs) are a powerful framework for learning representations of graph-structured domains. However, weights in MPNNs act on features only, limiting their ability to capture structural patterns. We introduce a…

Machine Learning · Computer Science 2026-05-26 Florian Seiffarth

Equivariant Graph Neural Networks (GNNs) that incorporate E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models, EGNN leverages a simple scalarization technique to perform…

Machine Learning · Computer Science 2025-10-16 Jiacheng Cen , Anyi Li , Ning Lin , Yuxiang Ren , Zihe Wang , Wenbing Huang

Analyzing scalar and vector fields on the sphere, such as temperature or wind speed and direction on Earth, is a difficult task. Models should respect both the rotational symmetries of the sphere and the inherent symmetries of the vector…

Machine Learning · Computer Science 2026-04-01 Francesco Ballerin , Nello Blaser , Erlend Grong

Graph neural networks (GNNs) have shown considerable promise in computational chemistry. However, the limited availability of molecular data raises concerns regarding GNNs' ability to effectively capture the fundamental principles of…

Machine Learning · Computer Science 2025-03-12 Junyi An , Chao Qu , Yun-Fei Shi , XinHao Liu , Qianwei Tang , Fenglei Cao , Yuan Qi

Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of…

Machine Learning · Computer Science 2024-03-13 Yang Liu , Jiashun Cheng , Haihong Zhao , Tingyang Xu , Peilin Zhao , Fugee Tsung , Jia Li , Yu Rong

We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve…

Machine Learning · Computer Science 2023-11-21 Chaoran Cheng , Jian Peng

Neural networks that incorporate geometric relationships respecting SE(3) group transformations (e.g. rotations and translations) are increasingly important in molecular applications, such as molecular property prediction, protein structure…

Machine Learning · Computer Science 2025-10-21 Jose Siguenza , Bharath Ramsundar

Invariant models, one important class of geometric deep learning models, are capable of generating meaningful geometric representations by leveraging informative geometric features in point clouds. These models are characterized by their…

Machine Learning · Computer Science 2025-06-17 Zian Li , Xiyuan Wang , Shijia Kang , Muhan Zhang

Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symmetries can lead to overconstrained weights and decreased…

Machine Learning · Computer Science 2025-05-09 Lars Veefkind , Gabriele Cesa

Local gauge symmetry underlies fundamental interactions and strongly correlated quantum matter, yet existing machine-learning approaches lack a general, principled framework for learning under site-dependent symmetries, particularly for…

Strongly Correlated Electrons · Physics 2026-04-23 Ali Rayat , Yaohang Li , Gia-Wei Chern

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, \emph{e.g.}, translations,…

Machine Learning · Computer Science 2024-06-11 Liming Wu , Zhichao Hou , Jirui Yuan , Yu Rong , Wenbing Huang

Being able to identify regions within or around proteins, to which ligands can potentially bind, is an essential step to develop new drugs. Binding site identification methods can now profit from the availability of large amounts of 3D…

Modeling molecular potential energy surface is of pivotal importance in science. Graph Neural Networks have shown great success in this field. However, their message passing schemes need special designs to capture geometric information and…

Machine Learning · Computer Science 2023-04-24 Xiyuan Wang , Muhan Zhang

Computational materials discovery is limited by the high cost of first-principles calculations. Machine learning (ML) potentials that predict energies from crystal structures are promising, but existing methods face computational…

A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs). Such GCNs utilize isotropic kernels and are therefore insensitive to the relative orientation of vertices and…

Machine Learning · Computer Science 2021-11-22 Pim de Haan , Maurice Weiler , Taco Cohen , Max Welling

Heterogeneous graph neural networks (HGNNs) have powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations. Existing HGNNs inherit many mechanisms from graph neural networks…

Machine Learning · Computer Science 2023-09-04 Xiaocheng Yang , Mingyu Yan , Shirui Pan , Xiaochun Ye , Dongrui Fan

Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

Incorporating inductive biases into ML models is an active area of ML research, especially when ML models are applied to data about the physical world. Equivariant Graph Neural Networks (GNNs) have recently become a popular method for…

Machine Learning · Computer Science 2023-11-07 Savannah Thais , Daniel Murnane

3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry…

Machine Learning · Computer Science 2024-12-11 Elyssa Hofgard , Rui Wang , Robin Walters , Tess Smidt

Spatial networks are networks whose graph topology is constrained by their embedded spatial space. Understanding the coupled spatial-graph properties is crucial for extracting powerful representations from spatial networks. Therefore,…

Machine Learning · Computer Science 2024-01-11 Zheng Zhang , Sirui Li , Jingcheng Zhou , Junxiang Wang , Abhinav Angirekula , Allen Zhang , Liang Zhao