Crystal-GFN: sampling crystals with desirable properties and constraints - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Crystal-GFN: sampling crystals with desirable properties and constraints


Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such as electrocatalysts, superionic conductors or photovoltaic materials can have a crucial impact, for instance, in improving the efficiency of renewable energy production and storage. In this paper, we introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials, namely the space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physical and structural constraints, as well as the use of any available predictive model of a desired physico-chemical property as an objective function. To design stable materials, one must target the candidates with the lowest formation energy, which is used as an objective to evaluate the capabilities of Crystal-GFN. The formation energy of a crystal structure is predicted here by a new proxy model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample diverse crystals with low formation energy.
Fichier principal
Vignette du fichier
73_crystal_gfn_sampling_materials.pdf (4.77 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04407903 , version 1 (21-01-2024)




  • HAL Id : hal-04407903 , version 1


Alex Hernandez-Garcia, Alexandre Duval, Alexandra Volokhova, Yoshua Bengio, Divya Sharma, et al.. Crystal-GFN: sampling crystals with desirable properties and constraints. AI4MAt 2023 - AI for Accelerated Materials Design workshop at 37th Conference on Neural Information Processing Systems (NeurIPS 2023) - AI4MAt workshop, Dec 2023, New Orleans (Louisiana), United States. ⟨hal-04407903⟩
83 View
306 Download


Gmail Facebook X LinkedIn More