Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911139374301184 |
|---|---|
| author | Gouvêa, Rogério Almeida De Breuck, Pierre-Paul Pretto, Tatiane Rignanese, Gian-Marco Santos, Marcos José Leite |
| author_facet | Gouvêa, Rogério Almeida De Breuck, Pierre-Paul Pretto, Tatiane Rignanese, Gian-Marco Santos, Marcos José Leite |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03547 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability Gouvêa, Rogério Almeida De Breuck, Pierre-Paul Pretto, Tatiane Rignanese, Gian-Marco Santos, Marcos José Leite Materials Science Machine Learning 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. |
| title | Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability |
| topic | Materials Science Machine Learning |
| url | https://arxiv.org/abs/2509.03547 |