Offline Materials Optimization with CliqueFlowmer

TL;DR

CliqueFlowmer is a novel offline model-based optimization method that enhances materials discovery by directly optimizing target properties, outperforming traditional generative models in generating superior materials.

Contribution

The paper introduces CliqueFlowmer, a domain-specific model integrating clique-based MBO with transformer and flow generation for improved materials optimization.

Findings

Materials generated by CliqueFlowmer outperform generative baselines.

The model effectively incorporates target property optimization into material generation.

Code and resources are publicly available for further research.

Abstract

Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling methods are ineffective at boldly exploring attractive regions of the materials space due to their maximum likelihood training. In this work, we offer an alternative CMD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. To that end, we introduce a domain-specific model, dubbed CliqueFlowmer, that incorporates recent advances of clique-based MBO into transformer and flow generation. We validate this model's optimization abilities and show that materials it produces strongly outperform those from generative baselines. To support specialized materials discovery applications and broader interdisciplinary research, we release our code, model weights, and additional project resources at https://github.com/znowu/CliqueFlowmer, https://colab.research.google.com/drive/1usUg7zezFkcYHlm2MdYwZUNJXf_YkWnY?usp=sharing, and https://x.com/kuba_AI/status/2033382617442345321.