EUVIMEDEUVIMED entdecken
Crossref

A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization

Haomin Yu, Jilin Hu, Yunyao Cheng, Chenjuan Guo, Yizhou Zhu, Bin Yang, Christian S. Jensen

IEEE Transactions on Knowledge and Data Engineering · 2026-08 · 38 (8) · 4823-4835

DOI: 10.1109/tkde.2026.3701591 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-08. Verfasst von Haomin Yu und 6 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the field of material science, the analysis of the properties of crystalline materials is of key importance. Recently, machine learning has become a prominent tool for predicting the properties of materials based on their structure. However, the application of machine learning to crystal property prediction faces two significant challenges. The first is the scarcity of labeled data, due to the time-consuming and resource-intensive process of crystal property labeling. The second is the importance of leveraging specialized knowledge when performing crystal structure analysis, which requires adapting machine learning methods specifically for the crystal domain. In this paper, we propose a new semi-supervised framework, a Knowledge-Based Semi-Supervised crystal property prediction (KBSS) framework, which employs consistency regularization to leverage both labeled and unlabeled data while incorporating crystal knowledge guidance. Specifically, to use unlabeled data efficiently, the KBSS framework incorporates two key modules: a knowledge-guided augmentation (KGA) module and an adaptive pseudo-label filtering (APF) module. The KGA module utilizes the Monte Carlo method to leverage knowledge from the crystal domain to guide weak and strong augmentations of crystal structures. The APF module enhances the pseudo-labeling process for unlabeled crystal data by enabling task-guided uncertainty adjustment and category-aware pseudo-label selection. The experimental results show that KBSS achieves state-of-the-art performance.

Zitieren

APA

Yu, H., Hu, J., Cheng, Y., Guo, C., Zhu, Y., Yang, B., & Jensen, C. S. (2026). A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization. IEEE Transactions on Knowledge and Data Engineering, 38(8), 4823-4835. https://doi.org/10.1109/tkde.2026.3701591

Vancouver

Yu H, Hu J, Cheng Y, Guo C, Zhu Y, Yang B, et al. A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization. IEEE Transactions on Knowledge and Data Engineering. 2026;38(8):4823-4835. doi:10.1109/tkde.2026.3701591

BibTeX
@article{Yu2026,
  author = {Yu, Haomin and Hu, Jilin and Cheng, Yunyao and Guo, Chenjuan and Zhu, Yizhou and Yang, Bin and Jensen, Christian S.},
  title = {A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {8},
  pages = {4823--4835},
  doi = {10.1109/tkde.2026.3701591}
}
Kostenlos starten →