Graph Structure Learning with Variational Information Bottleneck
This addresses graph structure learning for GNN applications, offering a novel method to improve performance in noisy real-world scenarios, though it appears incremental as an advancement of the Information Bottleneck principle.
The paper tackles the problem of noisy or incomplete graph structures in Graph Neural Networks (GNNs) by proposing VIB-GSL, a framework that learns task-relevant graph structures using a variational information bottleneck approach, achieving superior effectiveness and robustness in experiments.
Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL advances the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of VIB-GSL.