Learning simple heuristic rules for classifying materials based on chemical composition

2025-05-05

AI Summary

Accurate classification of materials by metallic/insulating behavior and topological properties remains challenging under data-scarce conditions, where conventional rule-based methods suffer from high data demands and poor interpretability. Method: We propose a novel paradigm for learning interpretable, chemistry-informed heuristic rules directly from elemental composition—without requiring crystal structure information. Crucially, we encode the periodic table’s inherent structure as a chemistry-aware inductive bias, integrating it into both feature engineering and rule learning. Contribution/Results: Our approach significantly improves few-shot generalization: achieving comparable test accuracy with 40% less training data. The derived rules are concise, human-readable, and semantically grounded in physical principles (e.g., electronegativity trends, orbital filling). By bridging symbolic reasoning with domain knowledge, our method overcomes the opacity of deep learning while maintaining high predictive performance—offering a principled, interpretable pathway for intelligent materials classification in low-data regimes.

Technology Category

• Data Mining & Knowledge Management: Rule Mining & Pattern Mining
• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

In the past decade, there has been a significant interest in the use of machine learning approaches in materials science research. Conventional deep learning approaches that rely on complex, nonlinear models have become increasingly important in computational materials science due to their high predictive accuracy. In contrast to these approaches, we have shown in a recent work that a remarkably simple learned heuristic rule -- based on the concept of topogivity -- can classify whether a material is topological using only its chemical composition. In this paper, we go beyond the topology classification scenario by also studying the use of machine learning to develop simple heuristic rules for classifying whether a material is a metal based on chemical composition. Moreover, we present a framework for incorporating chemistry-informed inductive bias based on the structure of the periodic table. For both the topology classification and the metallicity classification tasks, we empirically characterize the performance of simple heuristic rules fit with and without chemistry-informed inductive bias across a wide range of training set sizes. We find evidence that incorporating chemistry-informed inductive bias can reduce the amount of training data required to reach a given level of test accuracy.

Problem

• Classify materials as topological using chemical composition
• Develop heuristic rules to identify metallic materials compositionally
• Reduce training data needs with chemistry-informed inductive bias

Innovation

• Simple heuristic rules for material classification
• Chemistry-informed inductive bias framework
• Topogivity-based topological material classification