# SA-GAT-SR: Self-Adaptable Graph Attention Networks with Symbolic Regression for high-fidelity material property prediction

arXiv: https://arxiv.org/abs/2505.00625 · HTML: https://mlsanity.com/paper/2505.00625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 61 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Graph Neural Networks with Learnable Structural and Positional Representations](https://mlsanity.com/paper/2110.07875/) (2021)
- [Order Matters: Sequence to sequence for sets](https://mlsanity.com/paper/1511.06391/) (2015)
- [Structure-Aware Transformer for Graph Representation Learning](https://mlsanity.com/paper/2202.03036/) (2022)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [Orbital Graph Convolutional Neural Network for Material Property Prediction](https://mlsanity.com/paper/2008.06415/) (2020)
- [Structure-based out-of-distribution (OOD) materials property prediction: a benchmark study](https://mlsanity.com/paper/2401.08032/) (2024)
- [Graph Attention Networks with Positional Embeddings](https://mlsanity.com/paper/2105.04037/) (2021)
- [DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules](https://mlsanity.com/paper/2501.03278/) (2025)
- [GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation](https://mlsanity.com/paper/2403.15520/) (2024)
- [Formula graph self-attention network for representation-domain independent materials discovery](https://mlsanity.com/paper/2201.05649/) (2022)
- [Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/2207.13779/) (2022)
- [Automated discovery of symbolic laws governing skill acquisition from naturally occurring data](https://mlsanity.com/paper/2404.05689/) (2024)
- [Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification](https://mlsanity.com/paper/2111.11482/) (2021)
- [Automatic Graph Topology-Aware Transformer](https://mlsanity.com/paper/2405.19779/) (2024)
- [Domain-informed graph neural networks: a quantum chemistry case study](https://mlsanity.com/paper/2208.11934/) (2022)

## Abstract (arXiv)

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm, Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR), that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 times acceleration compared to conventional SR implementations that heavily rely on first principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.