Physical regularized Hierarchical Generative Model for Metallic Glass Structural Generation and Energy Prediction

TL;DR

This paper introduces GlassVAE, a hierarchical graph variational autoencoder that generates realistic atomic structures of metallic glasses and predicts their energies by incorporating physics-informed regularizers, improving efficiency and accuracy.

Contribution

The paper presents a novel physics-regularized hierarchical graph VAE for disordered materials, enabling realistic structure generation and energy prediction with invariant embeddings.

Findings

Regularizers significantly improve structure realism and energy accuracy.

GlassVAE efficiently explores the glass energy landscape.

Model outperforms existing methods in structure and energy prediction.

Abstract

Disordered materials such as glasses, unlike crystals, lack long range atomic order and have no periodic unit cells, yielding a high dimensional configuration space with widely varying properties. The complexity not only increases computational costs for atomistic simulations but also makes it difficult for generative AI models to deliver accurate property predictions and realistic structure generation. In this work, we introduce GlassVAE, a hierarchical graph variational autoencoder that uses graph representations to learn compact, rotation, translation, and permutation invariant embeddings of atomic configurations. The resulting structured latent space not only enables efficient generation of novel, physically plausible structures but also supports exploration of the glass energy landscape. To enforce structural realism and physical fidelity, we augment GlassVAE with two physics informed regularizers, a radial distribution function (RDF) loss that captures characteristic short and medium range ordering and an energy regression loss that reflects the broad configurational energetics. Both theoretical analysis and experimental results highlight the critical impact of these regularizers. By encoding high dimensional atomistic data into a compact latent vector and decoding it into structures with accurate energy predictions, GlassVAE provides a fast, physics aware path for modeling and designing disordered materials.