MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data
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_ | 1866915239875837952 |
|---|---|
| author | Li, Wentao Chen, Yizhe Qiu, Jiangjie Wang, Xiaonan |
| author_facet | Li, Wentao Chen, Yizhe Qiu, Jiangjie Wang, Xiaonan |
| contents | Data scarcity and the high cost of annotation have long been persistent challenges in the field of materials science. Inspired by its potential in other fields like computer vision, we propose the MatWheel framework, which train the material property prediction model using the synthetic data generated by the conditional generative model. We explore two scenarios: fully-supervised and semi-supervised learning. Using CGCNN for property prediction and Con-CDVAE as the conditional generative model, experiments on two data-scarce material property datasets from Matminer database are conducted. Results show that synthetic data has potential in extreme data-scarce scenarios, achieving performance close to or exceeding that of real samples in all two tasks. We also find that pseudo-labels have little impact on generated data quality. Future work will integrate advanced models and optimize generation conditions to boost the effectiveness of the materials data flywheel. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09152 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data Li, Wentao Chen, Yizhe Qiu, Jiangjie Wang, Xiaonan Machine Learning Materials Science Data scarcity and the high cost of annotation have long been persistent challenges in the field of materials science. Inspired by its potential in other fields like computer vision, we propose the MatWheel framework, which train the material property prediction model using the synthetic data generated by the conditional generative model. We explore two scenarios: fully-supervised and semi-supervised learning. Using CGCNN for property prediction and Con-CDVAE as the conditional generative model, experiments on two data-scarce material property datasets from Matminer database are conducted. Results show that synthetic data has potential in extreme data-scarce scenarios, achieving performance close to or exceeding that of real samples in all two tasks. We also find that pseudo-labels have little impact on generated data quality. Future work will integrate advanced models and optimize generation conditions to boost the effectiveness of the materials data flywheel. |
| title | MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data |
| topic | Machine Learning Materials Science |
| url | https://arxiv.org/abs/2504.09152 |