Pith. sign in

REVIEW 7 cited by

Geometric and Physical Quantities Improve E(3) Equivariant Message Passing

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 2110.02905 v3 pith:SKITPXJE submitted 2021-10-06 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords steerableequivariantgraphinformationmessagenetworksattributeschemistry
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that generalise equivariant graph networks, such that node and edge attributes are not restricted to invariant scalars, but can contain covariant information, such as vectors or tensors. This model, composed of steerable MLPs, is able to incorporate geometric and physical information in both the message and update functions. Through the definition of steerable node attributes, the MLPs provide a new class of activation functions for general use with steerable feature fields. We discuss ours and related work through the lens of equivariant non-linear convolutions, which further allows us to pin-point the successful components of SEGNNs: non-linear message aggregation improves upon classic linear (steerable) point convolutions; steerable messages improve upon recent equivariant graph networks that send invariant messages. We demonstrate the effectiveness of our method on several tasks in computational physics and chemistry and provide extensive ablation studies.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 11 citations worldwide. Full citation record

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

    cs.LG 2026-04 conditional novelty 6.5 of 10

    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.

  2. DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

    q-bio.BM 2025-06 conditional novelty 6.0 of 10

    A dual-space, hierarchically pooled equivariant GNN reports lower error than seven geometric baselines on RNA and protein property-prediction benchmarks.

  3. Cosmology with Topological Deep Learning

    astro-ph.CO 2025-05 conditional novelty 6.0 of 10

    Topological neural networks using tetrahedra, clusters and hyperedges built from halo catalogs lower inference error on Omega_m by 22% and on sigma_8 by up to 60% versus graph neural networks on Quijote.

  4. Thickness-aware E(3)-Equivariant 3D Mesh Neural Networks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A mesh GNN that links opposite surfaces via learned thickness edges improves node-level 3D deformation prediction while a PCA-based canonical coordinate system preserves E(3) equivariance.

  5. STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A flow-matching model that builds its starting noise from random walks matched to the observed motion produces more accurate trajectory predictions with only 5 integration steps.

  6. Bayesian Prior Construction for Uncertainty Quantification in First-Principles Statistical Mechanics

    cond-mat.stat-mech 2025-09 accept novelty 5.0 of 10

    Bayesian hyperparameter selection and ground-state-enforcing priors are compared for cluster expansions; standard posteriors rarely reproduce DFT ground states, and cone-restricted priors fix this.

  7. cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending

    cs.LG 2025-08 reject novelty 5.0 of 10

    cMALC-D uses an LLM to generate training contexts for multi-agent RL and a diversity-blending mechanism to avoid mode collapse, claiming improved generalization on traffic signal control.

Pith tools