FAENet: Frame Averaging Equivariant GNN for Materials Modeling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

FAENet: Frame Averaging Equivariant GNN for Materials Modeling


Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetries via the model architecture, which often reduces their expressivity, scalability and comprehensibility. In this paper, we introduce (1) a flexible framework relying on stochastic frame-averaging (SFA) to make any model E(3)-equivariant or invariant through data transformations. (2) FAENet: a simple, fast and expressive GNN, optimized for SFA, that processes geometric information without any symmetrypreserving design constraints. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling on the OC20 dataset (S2EF, IS2RE) as well as common molecular modeling tasks (QM9, QM7-X). A package implementation is available at https: //faenet.readthedocs.io.
Fichier principal
Vignette du fichier
2305.05577 (8).pdf (792.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04368760 , version 1 (01-01-2024)


  • HAL Id : hal-04368760 , version 1


Alexandre Duval, Victor Schmidt, Alex Hernandez, Santiago Miret, Fragkiskos D. Malliaros, et al.. FAENet: Frame Averaging Equivariant GNN for Materials Modeling. ICML 2023 - International Conference on Machine Learning, Jul 2023, Hawaii, United States. ⟨hal-04368760⟩
15 View
12 Download


Gmail Facebook X LinkedIn More