Pith. sign in

REVIEW 19 cited by

E(n) Equivariant Graph Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.09844 v3 pith:FERTZIGU submitted 2021-02-19 cs.LG stat.ML

E(n) Equivariant Graph Neural Networks

classification cs.LG stat.ML
keywords graphequivariantnetworksneuralexistingmethodsmodelspaces
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

    cs.CV 2026-06 unverdicted novelty 7.0

    Constructs G-equivariant ViTs for arbitrary discrete G ≤ O(2), proves H ≤ G implies G-models embed into H-models and single-head equivariant attention realizes all ordinary G-equivariant maps, introduces D6 hexagonal ...

  2. A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

    cs.CV 2026-06 unverdicted novelty 7.0

    A unified family of vision transformers equivariant to arbitrary discrete subgroups of O(2), with embedding and expressivity theorems, a D6 construction using hexagonal patches, and experiments on aerial images in low...

  3. PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty

    cs.LG 2026-04 unverdicted novelty 7.0

    PiGGO integrates a learned graph neural ODE as the continuous-time dynamics model within an extended Kalman filter to enable online virtual sensing and uncertainty-aware state estimation for nonlinear dynamic systems ...

  4. Estimating the triaxiality of massive clusters from 2D observables in MillenniumTNG with machine learning

    astro-ph.CO 2025-11 unverdicted novelty 7.0

    A CNN-GNN fusion model estimates triaxial cluster geometry from 2D X-ray, tSZ, and galaxy data in MillenniumTNG simulations, improving over spherical assumptions by 30% with R²=0.85 on major axis length and 71% accura...

  5. Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

    cs.LG 2026-04 conditional novelty 6.5

    Structure-pretrained diffusion plus an equivariant temporal interpolator generates chemically realistic MD trajectories on small molecules, tetrapeptides, and proteins by separating spatial and temporal learning.

  6. MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction

    cs.LG 2026-06 unverdicted novelty 6.0

    MMGNN decomposes molecular graphs into multi-color subgraphs by atom-type pairs and applies shared message-passing per subgraph, achieving top macro AUC-ROC of 0.838 on classification and best RMSE on ESOL and FreeSol...

  7. Scalable Inference-Time Annealing with Surrogate Likelihood Estimators

    cs.LG 2026-05 unverdicted novelty 6.0

    SITA performs scalable inference-time annealing of flow-based models on molecular systems by substituting energy-based surrogate likelihoods for divergence-based importance weights.

  8. Galactic Amnesia: The Information Washout of the Milky Way Merger History

    astro-ph.GA 2026-05 unverdicted novelty 6.0

    Mutual information analysis of TNG50 simulations shows gravitational potential and total energy retain merger mass and infall time information longest, while radial velocity loses it within ~5 Gyr, with washout depend...

  9. Graph Neural Network Predictions of Carbon 1s Binding Energies with Near-Experimental Accuracy

    physics.chem-ph 2026-04 conditional novelty 6.0

    An equivariant graph neural network predicts carbon 1s core-electron binding energies with 0.33 eV mean absolute error against 570 experimental values and transfers to molecules up to 45 atoms despite training on 4-16...

  10. Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation

    cs.LG 2026-04 unverdicted novelty 6.0

    EQUIMF is a unified equivariant framework that jointly generates discrete topologies and continuous geometries in molecular graphs via synchronized MeanFlow dynamics for efficient few-step sampling.

  11. Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation

    cs.LG 2026-03 unverdicted novelty 6.0

    EAD is an equivariant diffusion model with adaptive asynchronous denoising that achieves state-of-the-art 3D molecular conformation generation.

  12. InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames

    cs.LG 2025-10 conditional novelty 6.0

    An autoregressive transformer with inertial-frame tokenization and geometric rotary positional encoding reports state-of-the-art validity and stability on QM9, GEOM-Drugs, and B3LYP, plus strong functional-group-condi...

  13. Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing

    cs.LG 2025-10 unverdicted novelty 6.0

    Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.

  14. Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

    cs.LG 2021-04 accept novelty 6.0

    Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.

  15. Equivariant Graph Neural Networks Improve Optical Spectra Prediction for Materials Screening

    physics.optics 2026-06 unverdicted novelty 5.0

    Equivariant GNNs outperform prior models on optical spectra and static permittivity prediction using RPA datasets for materials screening.

  16. Loss-Guided Adaptive Scale Refinement for Molecular Force Prediction

    cs.LG 2026-06 unverdicted novelty 5.0

    Loss-guided adaptive scale refinement on NaCl aqueous system reduces overall force MAE from 399.65 to 381.23 by discovering intermediate scales from initial anchors.

  17. Graph Mamba Operator: A Latent Simulator for Interacting Particle Systems

    cs.LG 2026-06 unverdicted novelty 5.0

    GraMO couples graph interactions and temporal state updates in one linear recurrence with input-dependent coefficients to simulate N-body, motion, and robotics systems with lower long-horizon error than prior GNN or S...

  18. Machine Learning Interatomic Potentials: Advancing Open-Source Software for Efficient and Scalable Molecular Simulation

    physics.chem-ph 2026-05 unverdicted novelty 4.0

    mlip v2 is a new software release that integrates API redesign, e3j backend, eSEN model, improved charge modeling, and expanded simulation capabilities to support larger-scale molecular modeling.

  19. Graph Neural Network Predictions of Carbon 1s Binding Energies with Near-Experimental Accuracy

    physics.chem-ph 2026-04 unverdicted novelty 4.0

    Graph neural network achieves 0.33 eV MAE predicting experimental C 1s core-electron binding energies with demonstrated size transferability and E(3)-equivariance benefits.