Ordered-to-disordered transfer learning with graph neural networks for formation-energy and HOMO-LUMO gap prediction in high-entropy perovskite oxides
Abstract
High-entropy perovskite oxides (HEPOs) represent a chemically complex class of materials with promising functional properties, yet their vast compositional space and, chemical/structural disorder pose significant challenge for accurate property prediction. Graph neural networks (GNNs) enable rapid exploration of materials space but are often limited by the availability of representative training data. Here, we investigate ordered-to-disordered transfer learning using GNNs for formation-energy and HOMO-LUMO gap prediction in HEPOs by transferring knowledge learned from chemically ordered perovskites. Four representative GNN models, including CGCNN, GATGNN, ALIGNN and M3GNet are evaluated to understand the role of structural representations, spanning pairwise two-body and angular three-body interactions in transfer performance. We find strong property-dependent transfer behavior: formation-energy prediction transfers effectively to disordered HEPOs, whereas HOMO-LUMO gap prediction shows limited transferability due to its sensitivity to local chemical environments. Incorporating a small HEPO-specific training dataset substantially improves HOMO-LUMO gap prediction. Representation-level analysis using UMAP further highlights the importance of encoding three-body geometric information such as in ALIGNN for capturing complex structure-property relationships and improving transferability.
Related
- Machine learning prediction of DFT-derived electrical conductivity in perovskite and double perovskite materials using physically motivated descriptors
- Machine-Learning-Guided Prediction and Statistical Analysis of Electronic Bandgaps in Double-Perovskite Oxides for Photovoltaic and Optoelectronic Design
- Polymer Property Prediction via an Automated Molecular Dynamics Pipeline and Transfer Learning
- RedoxDB and RedEx: closing the DFT-experiment domain gap in redox potential prediction with transfer learning.
- Inter-Phase Chirality Transfer in 2D and Quasi-2D Perovskite Heterostructures
BibTeX
@misc{untarabut2026orderedtodisordered,
title = {{Ordered-to-disordered transfer learning with graph neural networks for formation-energy and HOMO-LUMO gap prediction in high-entropy perovskite oxides}},
author = {Panupol Untarabut and Narjes Jomaa and Sylvian Cadars and Olivier Masson and Samuel Bernard and Assil Bouzid and Santanu Saha},
howpublished = {HAL},
year = {2026},
month = jul,
eprint = {2607.29510},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05804949v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Ordered-to-disordered transfer learning with graph neural networks for formation-energy and HOMO-LUMO gap prediction in high-entropy perovskite oxides
AU - Panupol Untarabut
AU - Narjes Jomaa
AU - Sylvian Cadars
AU - Olivier Masson
AU - Samuel Bernard
AU - Assil Bouzid
AU - Santanu Saha
PY - 2026
DA - 2026/07/31
PB - HAL
UR - https://hal.science/hal-05804949v1
AB - High-entropy perovskite oxides (HEPOs) represent a chemically complex class of materials with promising functional properties, yet their vast compositional space and, chemical/structural disorder pose significant challenge for accurate property prediction. Graph neural networks (GNNs) enable rapid exploration of materials space but are often limited by the availability of representative training data. Here, we investigate ordered-to-disordered transfer learning using GNNs for formation-energy and HOMO-LUMO gap prediction in HEPOs by transferring knowledge learned from chemically ordered perovskites. Four representative GNN models, including CGCNN, GATGNN, ALIGNN and M3GNet are evaluated to understand the role of structural representations, spanning pairwise two-body and angular three-body interactions in transfer performance. We find strong property-dependent transfer behavior: formation-energy prediction transfers effectively to disordered HEPOs, whereas HOMO-LUMO gap prediction shows limited transferability due to its sensitivity to local chemical environments. Incorporating a small HEPO-specific training dataset substantially improves HOMO-LUMO gap prediction. Representation-level analysis using UMAP further highlights the importance of encoding three-body geometric information such as in ALIGNN for capturing complex structure-property relationships and improving transferability.
ER -