Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Informative Graph Structure Learning

About

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.

Shen Han, Zhiyao Zhou, Jiawei Chen, Sheng Zhou, Canghong Jin, Hai Lin, Da Zhong Li, Bingde Hu, Can Wang• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy85.83
583
Node ClassificationPubmed
Accuracy83
363
Node ClassificationRoman-Empire
Accuracy65.51
327
Node ClassificationOgbn-arxiv
Accuracy71.72
235
Node ClassificationCiteseer
Mean Accuracy74.35
202
Node-level classificationBlogCatalog
Accuracy0.9579
70
Node ClassificationCora 70% edge reduction level
Accuracy85.07
12
Node ClassificationCiteseer 70% edge reduction level
Accuracy73.16
12
Node ClassificationPubmed 70% edge reduction level
Accuracy82.91
12
Node ClassificationBlogcatalog 70% edge reduction level
Accuracy0.9524
12
Showing 10 of 11 rows

Other info

Follow for update