Equivariant Graph Neural Network

Equivariant Graph Neural Networks (EGNNs) aim to improve the efficiency and accuracy of machine learning models by incorporating the symmetries inherent in many scientific datasets, such as those representing molecules or physical systems. Current research focuses on developing more expressive EGNN architectures, including those based on Clifford algebras, polynomial functions, and message-passing mechanisms on higher-order structures like CW-complexes, often incorporating techniques like virtual nodes or discrete symmetries to enhance performance. These advancements are significantly impacting fields like drug discovery, materials science, and physics simulations by enabling more accurate and data-efficient modeling of complex systems.

Papers

May 24, 2023

April 13, 2023

Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks
Bingxin Zhou, Outongyi Lv, Kai Yi, Xinye Xiong, Pan Tan, Liang Hong, Yu Guang Wang
Protein Sequence Equivariant Graph Neural Network Protein Space Mutational Effect Prediction

April 11, 2023

Equivariant Graph Neural Networks for Charged Particle Tracking
Daniel Murnane, Savannah Thais, Ameya Thete
High Energy Physic Particle Tracking Equivariant Graph Neural Network Equivariant Architecture

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

March 3, 2023

Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
Yuyang Wang, Changwen Xu, Zijie Li, Amir Barati Farimani
Equivariant Graph Neural Network Molecular System Molecular Energy

February 23, 2023

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Yang Zhang, Zhewei Wei, Ye Yuan, Chongxuan Li, Wenbing Huang
Equivariant Graph Neural Network Binding Affinity Equivariant Message Protein Surface

January 25, 2023

E(n)-equivariant Graph Neural Cellular Automata
Gennaro Gala, Daniele Grattarola, Erik Quaeghebeur
Graph Neural Computational Model Cellular Automaton Equivariant Graph Neural Network Isotropic Network

November 6, 2022

Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
Francesco Saverio Pezzicoli, Guillaume Charpiat, François P. Landes
Graph Neural Network Transfer Learning Robust Representation Equivariant Graph Neural Network

October 27, 2022

Predicting Protein-Ligand Binding Affinity with Equivariant Line Graph Network
Yiqiang Yi, Xu Wan, Kangfei Zhao, Le Ou-Yang, Peilin Zhao
Protein Ligand Equivariant Graph Neural Network Affinity Prediction 3D Ligand Protein Ligand Binding

May 24, 2022

Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions
Masanobu Horie, Naoto Mitsume
Neural Network Graph Neural Network Neural PDE Solver Equivariant Graph Neural Network Boundary Condition Neural Partial Differential Equation Solver

March 12, 2022

Equivariant Graph Mechanics Networks with Constraints
Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
Participation Constraint Molecular Dynamic Equivariant Graph Neural Network Constrained Mechanical System Physic Informed Graph

February 20, 2022

Equivariant Graph Attention Networks for Molecular Property Prediction
Tuan Le, Frank Noé, Djork-Arné Clevert
Molecular Property Prediction Level Representation Equivariant Graph Neural Network 3D Molecule Scale Equivariant Equivariant Graph Attention

February 15, 2022

Geometrically Equivariant Graph Neural Networks: A Survey
Jiaqi Han, Yu Rong, Tingyang Xu, Wenbing Huang
Graph Neural Network Timely Survey Equivariant Graph Neural Network Geometric Graph

November 15, 2021

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne, Yatao Bian, Regina Barzilay, Tommi Jaakkola, Andreas Krause
Molecular Docking Equivariant Graph Neural Network Protein Engineering Se Equivariant Structure Refinement

Equivariant Graph Neural Network

Papers

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

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks

Equivariant Graph Neural Networks for Charged Particle Tracking

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

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

Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

E(n)-equivariant Graph Neural Cellular Automata

Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations

Predicting Protein-Ligand Binding Affinity with Equivariant Line Graph Network

Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditions

Equivariant Graph Mechanics Networks with Constraints

Equivariant Graph Attention Networks for Molecular Property Prediction

Geometrically Equivariant Graph Neural Networks: A Survey

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking