Offline Materials Optimization with CliqueFlowmer

2026-03-06

AI Summary

Traditional generative models struggle to efficiently explore high-performance regions in material space, limiting the optimization capabilities of computational materials discovery. This work proposes CliqueFlowmer, an offline model-based optimization (MBO) approach that integrates clique-based structural modeling, a Transformer architecture, and normalizing flows. It introduces, for the first time, a clique-based offline MBO framework into inverse materials design, enabling direct optimization toward target properties without relying on maximum likelihood training. Experimental results demonstrate that the generated materials significantly outperform existing generative baselines in terms of target performance. The code has been made publicly available to foster interdisciplinary applications.

Technology Category

Search and Optimization: Sampling/Simulation-based SearchMachine Learning: Graph-based Machine LearningCognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphsEconomics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applicationsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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 CliqueFlowmer's optimization abilities and show that materials it produces strongly outperform those provided by generative baselines. To enable employment of CliqueFlowmer in specialized materials optimization problems and support interdisciplinary research, we open-source our code at https://github.com/znowu/CliqueFlowmer.

Problem

• computational materials discovery
• materials optimization
• offline model-based optimization
• generative modeling
• target property optimization

Innovation

• offline model-based optimization
• CliqueFlowmer
• computational materials discovery
• clique-based MBO
• flow generation