Artificial intelligence (AI) can accelerate the design of materials by identifying correlations and complex patterns in data. However, AI methods commonly attempt to describe the entire, immense materials space with a single model, while it is typical that different mechanisms govern the materials behaviors across the materials space. The subgroup-discovery (SGD) approach identifies local rules describing exceptional subsets of data with respect to a given target. Thus, SGD can focus on mechanisms leading to exceptional performance. However, the identification of appropriate SG rules requires a careful consideration of the generality-exceptionality tradeoff. Here, we discuss challenges to advance the SGD approach in materials science and analyse the tradeoff between exceptionality and generality based on a Pareto front of SGD solutions.
@article{arxiv.2311.10381,
title = {Towards a Multi-Objective Optimization of Subgroups for the Discovery of Materials with Exceptional Performance},
author = {Lucas Foppa and Matthias Scheffler},
journal= {arXiv preprint arXiv:2311.10381},
year = {2023}
}