Equivariant Graph Neural Network for Crystalline Materials

Astrid Klipfel (1, 2, 3) , Zied Bouraoui (2) , Yaël Frégier (1) , Adlane Sayede (3)

1 LML - Laboratoire de Mathématiques de Lens
2 CRIL - Centre de Recherche en Informatique de Lens
3 UCCS Équipe Couches Minces & Nanomatériaux

Materials generation is an essential task in material science that aims to discover new materials. While most of the existing models have shown interesting results in simulation, they struggle to produce new original and stable materials. This paper discusses the salient properties required for material generation and studies the difficulties related to material pattern repetition, which impacts the stability of the generated structures.

Domaines: Intelligence artificielle [cs.AI]; Matériaux

Astrid Klipfel, Zied Bouraoui, Yaël Frégier, Adlane Sayede. Equivariant Graph Neural Network for Crystalline Materials. 1st International Workshop on Spatio-Temporal Reasoning and Learning, Jul 2022, JeJu, South Korea. ⟨hal-04037916⟩