Multi-View Graph Clustering via Node-Guided Contrastive Encoding

Multi-view clustering has gained significant attention for integrating multi-view information in multimedia applications. With the growing complexity of graph data, multi-view graph clustering (MVGC) has become increasingly important. Existing methods primarily use Graph Neural Networks (GNNs) to encode structural and feature information, but applying GNNs within contrastive learning poses specific challenges, such as integrating graph data with node features and handling both homophilic and heterophilic graphs. To address these challenges, this paper introduces Node-Guided Contrastive Encoding (NGCE), a novel MVGC approach that leverages node features to guide embedding generation. NGCE enhances compatibility with GNN filtering, effectively integrates homophilic and heterophilic information, and strengthens contrastive learning across views. Extensive experiments demonstrate its robust performance on six homophilic and heterophilic multi-view benchmark datasets.

NGCE (Node-Guided Contrastive Encoding) employs a node-guided encoding framework to address mixed homophilic and heterophilic patterns in multi-view graph clustering. This approach maintains the essential interactions between these patterns by avoiding their isolation and processing them within a unified framework. NGCE is designed to integrate graph data with node features effectively and strengthen contrastive learning across different views.