mlsanityData to 14 Oct 2026

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks

arXiv 2309.03139 ↗First posted 6 Sep 2023cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves performance across different physical systems benchmark tasks, with minimal differences in runtime or number of parameters. The proposed multichannel EGNN outperforms the standard singlechannel EGNN on N-body charged particle dynamics, molecular property predictions, and predicting the trajectories of solar system bodies. Given the additional benefits and minimal additional cost of multi-channel EGNN, we suggest that this extension may be of practical use to researchers working in machine learning for the physical sciences

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 25 of its 29 references that are in the map. First posted on arXiv 6 Sep 2023.

Builds on

25 of 29 references.

References · 25

  1. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  2. 2021E(n) Equivariant Graph Neural Networkscited by 965
  3. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  4. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  5. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
  6. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 441
  7. 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  9. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  10. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 255
  11. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  12. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
13 more
  1. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  2. 2021A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groupscited by 187
  3. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  4. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  5. 2022Equivariance with Learned Canonicalization Functionscited by 109
  6. 2022Rediscovering orbital mechanics with machine learningcited by 71
  7. 2022Equivariant Graph Mechanics Networks with Constraintscited by 68
  8. 2019Equivariant Flows: sampling configurations for multi-body systems with symmetric energiescited by 57
  9. 2020Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Propertiescited by 51
  10. 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
  11. 2022The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Sciencecited by 14
  12. 2022A Simple and Universal Rotation Equivariant Point-cloud Networkcited by 11
  13. 2021Geometric Algebra Attention Networks for Small Point Cloudscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 4.

10 papers.

  1. 2024Weisfeiler Leman for Euclidean Equivariant Machine Learningcited by 10
  2. 2024E(3)-Equivariant Mesh Neural Networkscited by 9
  3. 2024On the Expressive Power of Sparse Geometric MPNNscited by 7
  4. 2025Symmetry-Aware Generative Modeling through Learned Canonicalizationcited by 4
  5. 2025Scaling Laws and Symmetry, Evidence from Neural Force Fieldscited by 4
  6. 2025Frame-based Equivariant Diffusion Models for 3D Molecular Generationcited by 2
  7. 2026AMShortcut: An Inference- and Training-Efficient Inverse Design Model for Amorphous Materialscited by 1
  8. 2026AMGenC: Generating Charge Balanced Amorphous Materialscited by 0
  9. 2026Augmented Equivariant Mesh Networks for Anatomical Segmentationcited by 0
  10. 2026Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphscited by 0