# Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability

arXiv: https://arxiv.org/abs/2509.03547 · HTML: https://mlsanity.com/paper/2509.03547/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 56 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Predicting materials properties without crystal structure: Deep representation learning from stoichiometry](https://mlsanity.com/paper/1910.00617/) (2019)
- [Interpretable and Explainable Machine Learning for Materials Science and Chemistry](https://mlsanity.com/paper/2111.01037/) (2021)
- [Connectivity Optimized Nested Graph Networks for Crystal Structures](https://mlsanity.com/paper/2302.14102/) (2023)
- [Leveraging neural network interatomic potentials for a foundation model of chemistry](https://mlsanity.com/paper/2506.18497/) (2025)
- [Naturally-meaningful and efficient descriptors: machine learning of material properties based on robust one-shot ab initio descriptors](https://mlsanity.com/paper/2203.03392/) (2022)

## Built on by (most cited first, 1 of 1)

- [Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop](https://mlsanity.com/paper/2606.29717/) (2026)

## Abstract (arXiv)

This study introduces MatterVial, an innovative hybrid framework for feature-based machine learning in materials science. MatterVial expands the feature space by integrating latent representations from a diverse suite of pretrained graph neural network (GNN) models including: structure-based (MEGNet), composition-based (ROOST), and equivariant (ORB) graph networks, with computationally efficient, GNN-approximated descriptors and novel features from symbolic regression. Our approach combines the chemical transparency of traditional feature-based models with the predictive power of deep learning architectures. When augmenting the feature-based model MODNet on Matbench tasks, this method yields significant error reductions and elevates its performance to be competitive with, and in several cases superior to, state-of-the-art end-to-end GNNs, with accuracy increases exceeding 40% for multiple tasks. An integrated interpretability module, employing surrogate models and symbolic regression, decodes the latent GNN-derived descriptors into explicit, physically meaningful formulas. This unified framework advances materials informatics by providing a high-performance, transparent tool that aligns with the principles of explainable AI, paving the way for more targeted and autonomous materials discovery.