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

CSGCL: Community-Strength-Enhanced Graph Contrastive Learning

About

Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years. However, the underlying community semantics has not been well explored by most previous GCL methods. Research that attempts to leverage communities in GCL regards them as having the same influence on the graph, leading to extra representation errors. To tackle this issue, we define ''community strength'' to measure the difference of influence among communities. Under this premise, we propose a Community-Strength-enhanced Graph Contrastive Learning (CSGCL) framework to preserve community strength throughout the learning process. Firstly, we present two novel graph augmentation methods, Communal Attribute Voting (CAV) and Communal Edge Dropping (CED), where the perturbations of node attributes and edges are guided by community strength. Secondly, we propose a dynamic ''Team-up'' contrastive learning scheme, where community strength is used to progressively fine-tune the contrastive objective. We report extensive experiment results on three downstream tasks: node classification, node clustering, and link prediction. CSGCL achieves state-of-the-art performance compared with other GCL methods, validating that community strength brings effectiveness and generality to graph representations. Our code is available at https://github.com/HanChen-HUST/CSGCL.

Han Chen, Ziwen Zhao, Yuhua Li, Yixiong Zou, Ruixuan Li, Rui Zhang• 2023

Related benchmarks

TaskDatasetResultRank
Link PredictionPower
Hits@5036.22
28
Link PredictionE.coli
Hits@5084.16
28
Link PredictionC.ele
Hits@5071.7
28
Link PredictionPB
Hits@5049.42
28
Link PredictionUSAir
Hits@500.9016
28
Link PredictionYeast
Hits@5083.53
28
Link PredictionNS
Hits@5082.45
28
Link PredictionRouter
Hits@5045.59
17
Showing 8 of 8 rows

Other info

Follow for update