A Binded VAE for Inorganic Material Generation - ENSIIE
Conference Papers Year : 2021

A Binded VAE for Inorganic Material Generation

Abstract

Designing new industrial materials with desired properties can be very expensive and time consuming. The main difficulty is to generate compounds that correspond to realistic materials. Indeed, the description of compounds as vectors of components’ proportions is characterized by discrete features and a severe sparsity. Furthermore, traditional generative model validation processes as visual verification, FID and Inception scores are tailored for images and cannot then be used as such in this context. To tackle these issues, we develop an original Binded-VAE model dedicated to the generation of discrete datasets with high sparsity. We validate the model with novel metrics adapted to the problem of compounds generation. We show on a real issue of rubber compound design that the proposed approach outperforms the standard generative models which opens new perspectives for material design optimization
Fichier principal
Vignette du fichier
35_a_binded_vae_for_inorganic_mat.pdf (810.79 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04464893 , version 1 (12-07-2024)

Identifiers

Cite

Fouad Oubari, Antoine de Mathelin, Rodrigue Décatoire, Mathilde Mougeot. A Binded VAE for Inorganic Material Generation. NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, Dec 2012, Online, France. ⟨10.48550/arXiv.2112.09570⟩. ⟨hal-04464893⟩
110 View
13 Download

Altmetric

Share

More