Uncertainty-Aware Graph Structure Learning

TL;DR

This paper introduces UnGSL, an uncertainty-aware approach to graph structure learning that improves GNN performance by adaptively weighting node connections based on information quality, addressing limitations of existing methods.

Contribution

UnGSL is a novel plug-in module that estimates node uncertainty to refine graph structures, enhancing existing GSL methods without significant computational overhead.

Findings

UnGSL improves performance across six GSL methods.

Adaptive weighting based on uncertainty enhances graph quality.

Method is seamlessly integrable with minimal extra cost.

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 suboptimal. 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 ambiguous 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.