About this document
Multi-View Contrastive Graph Clustering by Yijian Fan is a document available to read on EtoBox.
This document discusses a proposed method called Multi-view Contrastive Graph Clustering (MCGC) for clustering multi-view attributed graph data. MCGC learns a new consensus graph by exploring information across attributes and graphs, rather than using the initial graph, to address issues with noise and incompleteness. It includes three key components: graph filtering to obtain a smoothed representation, graph learning to generate a consensus graph with adaptive view weighting, and graph contrastive learning
- Author
- Yijian Fan
- Language
- EN