Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning
ACM Transactions on Intelligent Systems and Technology · 28.02.2025 · 16 (1) · 1-21
DOI: 10.1145/3706115 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 25.01.2025. Verfasst von Cuiying Huo und 7 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Heterogeneous graph neural network (HGNN) is a popular technique for modeling and analyzing heterogeneous graphs. Most existing HGNN-based approaches are supervised or semi-supervised learning methods requiring graphs to be annotated, which is costly and time-consuming. Self-supervised contrastive learning has been proposed to address the problem of requiring annotated data by mining intrinsic properties in the given data. However, the existing contrastive learning methods are not suitable for heterogeneous graphs because they construct contrastive views only based on data perturbation or pre-defined structural properties (e.g., meta-path) in graph data while ignoring noises in node attributes and graph topologies. We develop a robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidances of node attributes and graph topologies and integrates and enhances them by a reciprocally contrastive mechanism to better model heterogeneous graphs. In this new approach, we adopt distinct but suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately. We further use both attribute similarity and topological correlation to construct high-quality contrastive samples. Extensive experiments on four large real-world heterogeneous graphs demonstrate the superiority and robustness of HGCL over several state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Huo, C., He, D., Li, Y., Jin, D., Dang, J., Pedrycz, W., Wu, L., & Zhang, W. (2025). Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning. ACM Transactions on Intelligent Systems and Technology, 16(1), 1-21. https://doi.org/10.1145/3706115
Vancouver
Huo C, He D, Li Y, Jin D, Dang J, Pedrycz W, et al. Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning. ACM Transactions on Intelligent Systems and Technology. 2025;16(1):1-21. doi:10.1145/3706115
BibTeX
@article{Huo2025,
author = {Huo, Cuiying and He, Dongxiao and Li, Yawen and Jin, Di and Dang, Jianwu and Pedrycz, Witold and Wu, Lingfei and Zhang, Weixiong},
title = {Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2025},
volume = {16},
number = {1},
pages = {1--21},
doi = {10.1145/3706115}
}
EUVIMED