Composable Crystals: Controllable Materials Discovery via Concept Learning
For materials scientists, this provides a controllable method for generating novel crystals, addressing the lack of control in existing black-box approaches.
The paper introduces a concept-based compositional framework for crystal generation that uses a vector-quantized variational autoencoder to discover reusable crystal concepts, enabling controllable exploration beyond training distribution. On MP-20 and Alex-MP-20, compositing concepts improves the V.S.U.N metric by up to 53.2% and 51.7%, with significant gains in novelty.
De novo crystal generation, a central task in materials discovery, aims to generate crystals that are simultaneously valid, stable, unique, and novel. Existing methods mainly rely on black-box stochastic sampling, providing limited control over how generated structures move beyond the observed distribution. In this paper, we introduce a concept-based compositional framework for crystal generation. We train a vector-quantized variational autoencoder to automatically discover a shared set of reusable crystal concepts, which serve as building blocks for guided generation. These learned concepts naturally exhibit interpretability from both local atomic environments and global symmetry patterns, and generalize to crystals from different distributions. By recombining such concepts, our framework enables controllable exploration of novel crystals beyond the training distribution, rather than relying solely on unconstrained random sampling. To further improve composition efficiency, we introduce a composition generator and iteratively refine it using high-quality samples generated by the model itself. The resulting concept compositions are then used to condition downstream crystal generation. Numerical experiments on MP-20 and Alex-MP-20 show that compositing concepts separately increase base model up to 53.2% and 51.7% on V.S.U.N metric, with particular gains in novelty.