Cluster-guided Contrastive Graph Clustering Network

TL;DR

This paper introduces CCGC, a graph clustering method that leverages high-confidence clustering results to improve positive and negative sample construction, enhancing clustering accuracy without complex data augmentations.

Contribution

The paper proposes a novel graph clustering network that uses high-confidence clustering guidance to select positive and negative samples, avoiding issues with data augmentation and unreliable negatives.

Findings

Outperforms existing state-of-the-art algorithms on six datasets.

Effectively constructs meaningful positive and negative samples guided by clustering confidence.

Demonstrates improved clustering accuracy and discriminative capability.

Abstract

Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samples are not reliable for ignoring important clustering information. To solve these problems, we propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms.