Equivariant Graph

Equivariant graph neural networks (GNNs) aim to leverage the inherent symmetries of data, such as rotational or translational invariance, to improve the efficiency and accuracy of machine learning models applied to graph-structured data. Current research focuses on developing architectures like SE(3)-equivariant and E(3)-equivariant GNNs, often incorporating hypergraphs to capture higher-order relationships, and employing techniques like relaxed weights to control symmetry breaking. These models find applications across diverse fields, including materials science (predicting elastic properties and homogenized responses), chemistry (molecular representation learning and NMR prediction), and biophysics (protein structure prediction and dynamics modeling), offering improved accuracy and interpretability compared to non-equivariant methods.

Papers

November 15, 2024

DuSEGO: Dual Second-order Equivariant Graph Ordinary Differential Equation
Yingxu Wang, Nan Yin, Mingyan Xiao, Xinhao Yi, Siwei Liu, Shangsong Liang
Graph Neural Network Graph Embeddings Diverse Equation Equivariant Graph Graph Ordinary Differential Equation

October 15, 2024

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
Jiacheng Cen, Anyi Li, Ning Lin, Yuxiang Ren, Zihe Wang, Wenbing Huang
Neural Network Level Representation Equivariant Graph Neural Network Equivariant Graph Steering Vector

October 10, 2024

Learning Equivariant Non-Local Electron Density Functionals
Nicholas Gao, Eike Eberhard, Stephan Günnemann
Non Local Equivariant Feature Equivariant Graph Length Extrapolation

July 30, 2024

Relaxed Equivariant Graph Neural Networks
Elyssa Hofgard, Rui Wang, Robin Walters, Tess Smidt
Equivariant Neural Network Cyclic Symmetry Equivariant Graph Neural Network Symmetry Breaking Equivariant Graph Euclidean Symmetry

May 26, 2024

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning
Hongfei Wu, Lijun Wu, Guoqing Liu, Zhirong Liu, Bin Shao, Zun Wang
Molecular Representation Equivariant Graph Equivariant Hypergraph Neural Network

April 5, 2024

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response
Ravi Patel, Cosmin Safta, Reese E. Jones
Convolutional Neural Network Individual Representation Constitutive Model Equivariant Graph Passive Symmetry Homogenization Approach

November 21, 2023

Carbohydrate NMR chemical shift predictions using E(3) equivariant graph neural networks
Maria Bånkestad, Keven M. Dorst, Göran Widmalm, Jerk Rönnols
Neural Network Magnetic Resonance Equivariant Graph Nuclear Magnetic Resonance Chemical Shift Biomolecular Structure

June 22, 2023

StrainTensorNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks
Teerachote Pakornchote, Annop Ektarawong, Thiparat Chotibut
Neural Network Crystal Structure Atomistic System Price Elasticity Equivariant Graph Strain Energy

June 21, 2023

Predicting protein variants with equivariant graph neural networks
Antonia Boca, Simon Mathis
Neural Network Sequence Modeling Equivariant Graph Protein Stability Structure Based Model

May 30, 2023

Predicting protein stability changes under multiple amino acid substitutions using equivariant graph neural networks
Sebastien Boyer, Sam Money-Kyrle, Oliver Bent
Neural Network Protein Design Equivariant Graph Protein Stability

May 24, 2023

Learning Lagrangian Fluid Mechanics with E($3$)-Equivariant Graph Neural Networks
Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Stefan Adami, Nikolaus A. Adams
Equivariant Model Equivariant Graph Neural Network Physical Interaction Equivariant Graph Lagrangian Fluid

April 7, 2023

A new perspective on building efficient and expressive 3D equivariant graph neural networks
Weitao Du, Yuanqi Du, Limei Wang, Dieqiao Feng, Guifeng Wang, Shuiwang Ji, Carla Gomes, Zhi-Ming Ma
Neural Network New Perspective Equivariant Graph Neural Network Equivariant Graph Geometric Graph Neural Network Global Geometric

March 31, 2023

E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics
Artur P. Toshev, Gianluca Galletti, Johannes Brandstetter, Stefan Adami, Nikolaus A. Adams
Coarse Grained Equivariant Model Equivariant Graph Neural Network Particle Dynamic Equivariant Graph

February 22, 2023

Equivariant Polynomials for Graph Neural Networks
Omri Puny, Derek Lim, Bobak T. Kiani, Haggai Maron, Yaron Lipman
Graph Neural Network Expressive Power Equivariant Graph Permutation Equivariance

November 14, 2022

Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
Zimu Li, Zihan Pengmei, Han Zheng, Erik Thiede, Junyu Liu, Risi Kondor
Tensor Network Equivariant Neural Network Anti Unification Equivariant Representation Equivariant Graph Group Equivariant Neural Network

August 12, 2022

Conditional Antibody Design as 3D Equivariant Graph Translation
Xiangzhe Kong, Wenbing Huang, Yang Liu
Antibody Design Equivariant Graph Equivariant Attention

June 7, 2022

Utility of Equivariant Message Passing in Cortical Mesh Segmentation
Dániel Unyi, Ferdinando Insalata, Petar Veličković, Bálint Gyires-Tóth
Task Utility Segmentation Result Graph Based Learning Equivariant Graph Equivariant Message Passing

May 20, 2022

EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures
Alex Morehead, Xiao Chen, Tianqi Wu, Jian Liu, Jianlin Cheng
Direct Assessment Equivariant Graph Protein Complex Protein Complex Structure

May 15, 2022

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang
Molecular Graph Conditional Generative Molecular Design Equivariant Neural Equivariant Graph

March 31, 2022

3D Equivariant Graph Implicit Functions
Yunlu Chen, Basura Fernando, Hakan Bilen, Matthias Nießner, Efstratios Gavves
Neural Implicit Representation Equivariant Graph Equivariant Layer 3D Transformation Equivariant Operation

Equivariant Graph

Papers

DuSEGO: Dual Second-order Equivariant Graph Ordinary Differential Equation

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?

Learning Equivariant Non-Local Electron Density Functionals

Relaxed Equivariant Graph Neural Networks

SE3Set: Harnessing equivariant hypergraph neural networks for molecular representation learning

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response

Carbohydrate NMR chemical shift predictions using E(3) equivariant graph neural networks

StrainTensorNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks

Predicting protein variants with equivariant graph neural networks

Predicting protein stability changes under multiple amino acid substitutions using equivariant graph neural networks

Learning Lagrangian Fluid Mechanics with E($3$)-Equivariant Graph Neural Networks

A new perspective on building efficient and expressive 3D equivariant graph neural networks

E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics

Equivariant Polynomials for Graph Neural Networks

Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism

Conditional Antibody Design as 3D Equivariant Graph Translation

Utility of Equivariant Message Passing in Cortical Mesh Segmentation

EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design

3D Equivariant Graph Implicit Functions