$\texttt{SynC}$: Synergistic Boosting of Structure and Representation for Deep Graph Clustering

ArXi:2406.15797v2 Announce Type: replace Employing graph neural networks (GNNs) for graph clustering has shown promising results in deep graph clustering. However, existing methods disregard the reciprocal relationship between representation learning and structure augmentation: the homogeneous the graph, the cohesive the node representations; the cohesive the node representations, the reliable the structure augmentation becomes. Moreover, the generalization ability of existing GNN-based models on the low homophily graph is relatively poor.