Optimizing Materials With CliqueFlowmer

Recent advances in deep learning inspired computational approaches to enhance material discovery (MD). A plethora of problems in this field involve finding materials that optimize a target property. Nevertheless, the increasingly popular generative modeling-based methods are ineffective at boldly exploring attractive regions of the material space due to their maximal likelihood training. In this work, we offer an alternative MD technique based on offline model-based optimization (MBO) that fuses direct optimization of a target material property into generation. For 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 CliqueFlowmer with respect to its ability to optimize the target property and show that, unlike generative baselines, it strongly shifts the material distribution in the favorable direction.