3 papers
cs.SI2025
CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learning
Yuecheng Li, Lele Fu, Sheng Huang +3
Recently, graph contrastive learning (GCL) has emerged as one of the optimal solutions for node-level and supervised tasks. However, for structure-related and unsupervised tasks su…
cs.LG2025
Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
Chuan Chen, Tianchi Liao, Xiaojun Deng +3
In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distribution…
cs.LG2025
THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
Bowen Deng, Tong Wang, Lele Fu +3
Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through selfsupervised learning and then apply K-means to the encoder output.…