Informative Graph Structure Learning

2026-05-16

AI Summary

This work addresses the excessive computational and memory overhead in existing graph structure learning methods, often caused by redundant edges. To mitigate this issue, the study introduces diversity into graph structure learning for the first time, proposing a novel edge construction strategy that jointly leverages node similarity and diversity. The resulting graph structure is optimized under mutual information guidance, enabling the method to function as a plug-and-play module compatible with prevailing frameworks. This approach significantly reduces the number of edges while simultaneously enhancing model performance. Extensive experiments demonstrate consistent and substantial performance gains across six state-of-the-art graph structure learning methods, validating the effectiveness and generalizability of the proposed technique.

Abstract

The quality of graph-structured data is fundamental to the success of modern graph analysis techniques such as Graph Neural Networks (GNNs). However, real-world graph data is often suboptimal, suffering from issues such as noise and incomplete connections. Graph Structure Learning (GSL) has emerged as a promising technique that adaptively optimizes node connections. However, we observe that the effectiveness of GSL often comes at the cost of a dramatic expansion in edge count, resulting in significant storage and computational overhead. In this work, we reveal that this limitation stems from the prevalent use of similarity-based edge construction, which predominantly connects highly similar neighbors based on their embeddings, introducing substantial structure redundancy. To address this, we propose a novel Informative Graph Structure Learning method (InGSL), which jointly considers both similarity and diversity in edge construction by incorporating a mutual-information-guided learning strategy. Notably, InGSL serves as a plug-in module that can be seamlessly integrated into existing GSL frameworks. Through extensive experiments on six representative GSL methods, we demonstrate that InGSL achieves significant performance improvements at a reduced number of edges.

Problem

• Graph Structure Learning
• structure redundancy
• edge sparsity
• graph-structured data
• similarity-based edge construction

Innovation

• Graph Structure Learning
• Mutual Information
• Edge Sparsification
• Diversity-aware Learning
• Plug-in Module