EquiHGNN: Scalable Rotationally Equivariant Hypergraph Neural Networks

TL;DR

EquiHGNN introduces a symmetry-aware hypergraph neural network framework that captures high-order molecular interactions, leading to improved modeling of large molecules by preserving geometric properties and integrating spatial features.

Contribution

The paper presents a novel equivariant hypergraph neural network architecture that effectively models high-order molecular interactions with symmetry constraints, enhancing performance on large-scale datasets.

Findings

High-order interactions benefit large molecules but limited for small ones.

Adding geometric features improves model performance.

Equivariant architectures outperform non-equivariant counterparts.

Abstract

Molecular interactions often involve high-order relationships that cannot be fully captured by traditional graph-based models limited to pairwise connections. Hypergraphs naturally extend graphs by enabling multi-way interactions, making them well-suited for modeling complex molecular systems. In this work, we introduce EquiHGNN, an Equivariant HyperGraph Neural Network framework that integrates symmetry-aware representations to improve molecular modeling. By enforcing the equivariance under relevant transformation groups, our approach preserves geometric and topological properties, leading to more robust and physically meaningful representations. We examine a range of equivariant architectures and demonstrate that integrating symmetry constraints leads to notable performance gains on large-scale molecular datasets. Experiments on both small and large molecules show that high-order interactions offer limited benefits for small molecules but consistently outperform 2D graphs on larger ones. Adding geometric features to these high-order structures further improves the performance, emphasizing the value of spatial information in molecular learning. Our source code is available at https://github.com/HySonLab/EquiHGNN/