Subgraph Collaborative Graph Contrastive Learning for Recommendation

Jie Ma, Jiwei Qin, Peichen Ji, Zhibin Yang, Donghao Zhang, Chaoqun Liu

Abstract: Graph Collaborative Filtering discovers potential connections between users and items using graph neural networks. However, graph neural networks may aggregate the noise in the user-item interaction data when updating node features. In addition, increasing the number of network layers may lead to the over-smoothing problem, whereby the representations of distinct nodes become excessively similar.