Interpretable Graph Neural Networks for Classifying Structure and Magnetism in Delafossite Compounds

TL;DR

This paper introduces an interpretable graph neural network model that accurately classifies delafossite structures and magnetic states, providing insights into the physical features influencing magnetic behavior in complex materials.

Contribution

It presents a gray-box AI approach that aligns learned representations with physical concepts, enhancing interpretability and understanding of magnetic properties in delafossite compounds.

Findings

Validation accuracies over 80% for magnetic ordering models

Successful alignment of learned features with nine physical descriptors

Mapping concept importance reveals interpretable physical trends

Abstract

Delafossites (ABC2, where A and B are metals and C is a chalcogen) are a versatile family of quantum materials and layered oxides/chalcogenides whose properties are highly sensitive to atomic composition and stacking geometry. Their broad chemical tunability makes them an ideal platform for large-scale combinatorial exploration and high-throughput computational screening with desirable quantum properties. In this work, we employ a Concept Whitening Graph Neural Network, a gray-box AI model, to classify delafossite structures by stacking sequence and magnetic states. By aligning learned representations with human-interpretable physical concepts, this gray-box approach enables both accurate prediction and insight into the structural and chemical features driving magnetic behavior. The magnetic-ordering models achieved validation accuracies exceeding 80 percent, with a further slight uptick observed in the model incorporating the largest number of concepts. Concept alignment analysis revealed measurable learning across nine physically meaningful descriptors, with coefficients of determination ranging from approximately 0.6 for the d-shell valence-electron concepts to 0.4-0.5 for the magnetic coupling parameters. Furthermore, we mapped the concept importances onto the material graph representation, elucidating interpretable physical trends and the progression of stable concept-aligned regions across training. These results demonstrate the potential of interpretable graph-based learning to capture the underlying physics of complex materials systems and provide an interpretable framework for accelerating the discovery and understanding of delafossites and related crystalline materials.