Graph Symbolic Distillation: Decoding Graph Data into Interpretable Formulas across Materials and Chemistry
Abstract
Graph data provide a natural representation of the interconnected structures and interactions underlying many chemical and materials systems. Graph neural networks (GNNs) can learn complex relationships from such data, yet translating these representations into interpretable descriptors and scientific insights remains challenging. Here we introduce graph symbolic distillation (GSD), a framework for decoding graph data into interpretable symbolic formulas. GSD identifies task-relevant message-passing architectures and distills their learned transformations while preserving graph connectivity and aggregation operations. Across three case studies spanning bulk materials, molecules, and surfaces, GSD not only recovers expert-defined descriptors from elementary node and edge features, but also reveals relationships emerging from their organization in complex graphs: extremal local geometric descriptors for band gap variations in γ-CsPbI3, a local polarity--size relationship underlying hydration free energy, and site-specific electronic--connectivity coupling in multidentate adsorption. GSD thus provides a general route from graph data to interpretable descriptors and new, testable scientific insights.
Related
- Conditional latent distillation enables controllable molecular generation in data-limited soft materials
- Chemistry-Informed Transfer and Interaction-Resolved Learning Towards Data-Efficient Materials Exploration
- From unstructured to structured: opportunities, risks and engineering practices for LLM-based data extraction in chemistry and materials
- Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis
- Measurement-efficient energy estimator for quantum chemistry of photodynamic materials
BibTeX
@misc{yao2026graph,
title = {{Graph Symbolic Distillation: Decoding Graph Data into Interpretable Formulas across Materials and Chemistry}},
author = {Yuxuan Yao and Harald Oberhofer and Karsten Reuter and Wenbin Xu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07719},
eprint = {2611.07719},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07719},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Graph Symbolic Distillation: Decoding Graph Data into Interpretable Formulas across Materials and Chemistry
AU - Yuxuan Yao
AU - Harald Oberhofer
AU - Karsten Reuter
AU - Wenbin Xu
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.07719
UR - https://arxiv.org/abs/2611.07719
AB - Graph data provide a natural representation of the interconnected structures and interactions underlying many chemical and materials systems. Graph neural networks (GNNs) can learn complex relationships from such data, yet translating these representations into interpretable descriptors and scientific insights remains challenging. Here we introduce graph symbolic distillation (GSD), a framework for decoding graph data into interpretable symbolic formulas. GSD identifies task-relevant message-passing architectures and distills their learned transformations while preserving graph connectivity and aggregation operations. Across three case studies spanning bulk materials, molecules, and surfaces, GSD not only recovers expert-defined descriptors from elementary node and edge features, but also reveals relationships emerging from their organization in complex graphs: extremal local geometric descriptors for band gap variations in γ-CsPbI_3, a local polarity--size relationship underlying hydration free energy, and site-specific electronic--connectivity coupling in multidentate adsorption. GSD thus provides a general route from graph data to interpretable descriptors and new, testable scientific insights.
ER -