A debiased graph clustering approach using dual contrastive learning

Node and graph-level clustering hold considerable significance for a wide range of applications, including drug target identification and protein function prediction. Recently, contrastive learning has surpassed numerous unsupervised learning methods and become increasingly useful for various deep clustering procedures, achieving commendable results. However, two primary obstacles impede further deployment of graph contrastive clustering: (1) its inherent tendency to separate node representations, which contradicts the clustering objective of forming meaningful groups and impedes effective cluster creation, and (2) the occurrence of false negative samples, which similarly obstructs cluster formation. Hence, this paper proposes a novel graph clustering algorithm, which employs a dual contrastive learning approach, encompassing element and cluster contrasts, and a strategy for debiasing false negative samples. The proposed algorithm utilizes element-level contrastive learning on embeddings derived from the encoder, integrating detailed node or graph characteristics. Then, clustering and cluster-level contrastive learning are executed in the embedding space to refine the results. Furthermore, the algorithm effectively addresses the potential false negatives and imbalanced prediction challenges during the dual-contrast process by implementing an optimization mechanism based on reliable results, thereby enhancing the clustering performance. Rigorous experiments across three node and graph-level benchmarks validate our proposed algorithm's efficacy.