Saved in:
Bibliographic Details
Main Authors: Wang, Botian, Ouyang, Yawen, Li, Yaohui, Pan, Mianzhi, Tang, Yuanhang, Wang, Yiqun, Cui, Haorui, Zhang, Jianbing, Wang, Xiaonan, Ma, Wei-Ying, Zhou, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.15483
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914362296369152
author Wang, Botian
Ouyang, Yawen
Li, Yaohui
Pan, Mianzhi
Tang, Yuanhang
Wang, Yiqun
Cui, Haorui
Zhang, Jianbing
Wang, Xiaonan
Ma, Wei-Ying
Zhou, Hao
author_facet Wang, Botian
Ouyang, Yawen
Li, Yaohui
Pan, Mianzhi
Tang, Yuanhang
Wang, Yiqun
Cui, Haorui
Zhang, Jianbing
Wang, Xiaonan
Ma, Wei-Ying
Zhou, Hao
contents Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa's potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15483
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoMa: A Modular Deep Learning Framework for Material Property Prediction
Wang, Botian
Ouyang, Yawen
Li, Yaohui
Pan, Mianzhi
Tang, Yuanhang
Wang, Yiqun
Cui, Haorui
Zhang, Jianbing
Wang, Xiaonan
Ma, Wei-Ying
Zhou, Hao
Machine Learning
Materials Science
Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa's potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration.
title MoMa: A Modular Deep Learning Framework for Material Property Prediction
topic Machine Learning
Materials Science
url https://arxiv.org/abs/2502.15483