Proceedings

Uncertainty-guided Graph Contrastive Learning from a Unified Perspective

Zhiqiang Li, Jie Wang, Jianqing Liang, Junbiao Cui, Xingwang Zhao, Jiye Liang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 5653-5661.

https://doi.org/10.24963/ijcai.2025/629

Keywords

  • Data Mining: DM: Mining graphs
  • Machine Learning: ML: Self-supervised Learning

Abstract

The success of current graph contrastive learning methods largely relies on the choice of data augmentation and contrastive objectives. However, most existing methods tend to optimize these two components independently, neglecting their potential interplay, which leads to suboptimal quality of the learned embeddings. To address this issue, we propose Uncertainty-guided Graph Contrastive Learning (UGCL) from a unified perspective. The core of our method is the introduction of sample uncertainty, a critical metric that quantifies the degree of class ambiguity within individual samples. On this basis, we design a novel multi-scale data augmentation strategy and a weighted graph contrastive loss function, both of which significantly enhance the quality of embeddings. Theoretically, we demonstrate that UGCL can coordinate overall optimization objectives through uncertainty, and through experiments, we show that it improves the performance of tasks such as node classification, node clustering, and link prediction, thereby verifying the effectiveness of our method.

Zhiqiang Li, Jie Wang, Jianqing Liang, Junbiao Cui, Xingwang Zhao, and Jiye Liang. 2025. Uncertainty-guided Graph Contrastive Learning from a Unified Perspective. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 5653–5661. https://doi.org/10.24963/ijcai.2025/629
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards