Community-Aware Efficient Graph Contrastive Learning via Personalized Self-Training

no code implementations • 18 Nov 2023 • Yuecheng Li, YanMing Hu, Lele Fu, Chuan Chen, Lei Yang, Zibin Zheng

However, for unsupervised and structure-related tasks such as community detection, current GCL algorithms face difficulties in acquiring the necessary community-level information, resulting in poor performance.

Community Detection Contrastive Learning +1

Migrate Demographic Group For Fair GNNs

no code implementations • 7 Jun 2023 • YanMing Hu, Tianchi Liao, Jialong Chen, Jing Bian, Zibin Zheng, Chuan Chen

To tackle this problem, we propose a brand new framework, FairMigration, which can dynamically migrate the demographic groups instead of keeping that fixed with raw sensitive attributes.

Fairness Graph Learning +1

Decoupling anomaly discrimination and representation learning: self-supervised learning for anomaly detection on attributed graph

no code implementations • 11 Apr 2023 • YanMing Hu, Chuan Chen, Bowen Deng, YuJing Lai, Hao Lin, Zibin Zheng, Jing Bian

DSLAD is a self-supervised method with anomaly discrimination and representation learning decoupled for anomaly detection.

Anomaly Detection Representation Learning +1