Dual Contrastive Attributed Graph Clustering Network. (arXiv:2206.07897v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07897

Attributed graph clustering is one of the most important tasks in graph
analysis field, the goal of which is to group nodes with similar
representations into the same cluster without manual guidance. Recent studies
based on graph contrastive learning have achieved impressive results in
processing graph-structured data. However, existing graph contrastive learning
based methods 1) do not directly address the clustering task, since the
representation learning and clustering process are separated; 2) depend too
much on graph data augmentation, which …

arxiv clustering cv graph network