2 papers
cs.LG2024
Provable Training for Graph Contrastive Learning
Yue Yu, Xiao Wang, Mengmei Zhang +2
Graph Contrastive Learning (GCL) has emerged as a popular training approach for learning node embeddings from augmented graphs without labels. Despite the key principle that maximi…
cs.SI2024
Learning Social Graph for Inactive User Recommendation
Nian Liu, Shen Fan, Ting Bai +6
Social relations have been widely incorporated into recommender systems to alleviate data sparsity problem. However, raw social relations don't always benefit recommendation due to…