Supervised Pretraining for Material Property Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rahman, Chowdhury Mohammad Abid, Romero, Aldo H., Gyawali, Prashnna K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908342573596672
author Rahman, Chowdhury Mohammad Abid
Romero, Aldo H.
Gyawali, Prashnna K.
author_facet Rahman, Chowdhury Mohammad Abid
Romero, Aldo H.
Gyawali, Prashnna K.
contents Accurate prediction of material properties facilitates the discovery of novel materials with tailored functionalities. Deep learning models have recently shown superior accuracy and flexibility in capturing structure-property relationships. However, these models often rely on supervised learning, which requires large, well-annotated datasets an expensive and time-consuming process. Self-supervised learning (SSL) offers a promising alternative by pretraining on large, unlabeled datasets to develop foundation models that can be fine-tuned for material property prediction. In this work, we propose supervised pretraining, where available class information serves as surrogate labels to guide learning, even when downstream tasks involve unrelated material properties. We evaluate this strategy on two state-of-the-art SSL models and introduce a novel framework for supervised pretraining. To further enhance representation learning, we propose a graph-based augmentation technique that injects noise to improve robustness without structurally deforming material graphs. The resulting foundation models are fine-tuned for six challenging material property predictions, achieving significant performance gains over baselines, ranging from 2% to 6.67% improvement in mean absolute error (MAE) and establishing a new benchmark in material property prediction. This study represents the first exploration of supervised pertaining with surrogate labels in material property prediction, advancing methodology and application in the field.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20112
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Supervised Pretraining for Material Property Prediction
Rahman, Chowdhury Mohammad Abid
Romero, Aldo H.
Gyawali, Prashnna K.
Machine Learning
Materials Science
Artificial Intelligence
Accurate prediction of material properties facilitates the discovery of novel materials with tailored functionalities. Deep learning models have recently shown superior accuracy and flexibility in capturing structure-property relationships. However, these models often rely on supervised learning, which requires large, well-annotated datasets an expensive and time-consuming process. Self-supervised learning (SSL) offers a promising alternative by pretraining on large, unlabeled datasets to develop foundation models that can be fine-tuned for material property prediction. In this work, we propose supervised pretraining, where available class information serves as surrogate labels to guide learning, even when downstream tasks involve unrelated material properties. We evaluate this strategy on two state-of-the-art SSL models and introduce a novel framework for supervised pretraining. To further enhance representation learning, we propose a graph-based augmentation technique that injects noise to improve robustness without structurally deforming material graphs. The resulting foundation models are fine-tuned for six challenging material property predictions, achieving significant performance gains over baselines, ranging from 2% to 6.67% improvement in mean absolute error (MAE) and establishing a new benchmark in material property prediction. This study represents the first exploration of supervised pertaining with surrogate labels in material property prediction, advancing methodology and application in the field.
title Supervised Pretraining for Material Property Prediction
topic Machine Learning
Materials Science
Artificial Intelligence
url https://arxiv.org/abs/2504.20112