Symbolic Learning for Material Discovery
This addresses the challenge of efficient material discovery for applications in climate change, sustainability, and healthcare, representing an incremental improvement with novel method aspects.
The paper tackles the problem of discovering new materials by searching for materials that maximize an expensive-to-evaluate function, introducing SyMDis, a symbolic learning-based optimization method that discovers near-optimal materials in large databases with sample efficiency, performing comparably to state-of-the-art optimizers while learning interpretable rules that generalize to unseen datasets in zero-shot evaluations.
Discovering new materials is essential to solve challenges in climate change, sustainability and healthcare. A typical task in materials discovery is to search for a material in a database which maximises the value of a function. That function is often expensive to evaluate, and can rely upon a simulation or an experiment. Here, we introduce SyMDis, a sample efficient optimisation method based on symbolic learning, that discovers near-optimal materials in a large database. SyMDis performs comparably to a state-of-the-art optimiser, whilst learning interpretable rules to aid physical and chemical verification. Furthermore, the rules learned by SyMDis generalise to unseen datasets and return high performing candidates in a zero-shot evaluation, which is difficult to achieve with other approaches.