Uncertainty-aware Graph Structure Learning

Shen Han, Zhiyao Zhou, Jiawei Chen, Zhezheng Hao, Sheng Zhou, Gang Wang, Yan Feng, Chun Chen, Can Wang

Track: Graph algorithms and modeling for the Web

Keywords: Graph structure learning, Graph neural network, Uncertainty

Abstract:

*Graph Neural Networks* (GNNs) have become a prominent approach for learning from graph-structured data. However, their effectiveness can be significantly compromised when the graph structure is sub-optimal. To address this issue, *Graph Structure Learning* (GSL) has emerged as a promising technique that refines node connections adaptively. Nevertheless, we identify two key limitations in existing GSL methods: 1) Most methods primarily focus on node similarity to construct relationships, while overlooking the quality of node information. Blindly connecting low-quality nodes and aggregating their ambitious information can degrade the performance of other nodes. 2) The constructed graph structures are often constrained to be symmetric, which may limit the model's flexibility and effectiveness.

To overcome these limitations, we propose an **Uncertainty-aware Graph Structure Learning** (UnGSL) strategy. UnGSL estimates the uncertainty of node information and utilizes it to adjust the strength of directional connections, where the influence of nodes with high uncertainty is adaptively reduced. Importantly, UnGSL serves as a plug-in module that can be seamlessly integrated into existing GSL methods with minimal additional computational cost. In our experiments, we implement UnGSL into six representative GSL methods, demonstrating consistent performance improvements.

Submission Number: 846