🤖 AI Summary
Existing unsupervised graph contrastive learning methods lack community-level awareness for structural tasks such as graph clustering and suffer from class collision and clustering unfairness due to reliance on negative sampling. This paper proposes an end-to-end joint learning framework that simultaneously optimizes community partitioning and node representation learning. First, we introduce a personalized self-training (PeST) strategy to enable fine-grained, community-level information modeling in a fully unsupervised manner. Second, we design an alignment-guided graph clustering (AlGC) module that unifies the self-training and downstream clustering spaces, jointly enhancing both performance and fairness. We theoretically establish the convergence of our framework and prove its fairness improvement. Extensive experiments on three multi-scale benchmark datasets demonstrate that our method achieves new state-of-the-art accuracy and normalized mutual information (NMI) for community detection, while significantly mitigating class collision.
📝 Abstract
In recent years, graph contrastive learning (GCL) has emerged as one of the optimal solutions for various supervised tasks at the node level. However, for unsupervised and structure-related tasks such as community detection, current GCL algorithms face difficulties in acquiring the necessary community-level information, resulting in poor performance. In addition, general contrastive learning algorithms improve the performance of downstream tasks by increasing the number of negative samples, which leads to severe class collision and unfairness of community detection. To address above issues, we propose a novel Community-aware Efficient Graph Contrastive Learning Framework (CEGCL) to jointly learn community partition and node representations in an end-to-end manner. Specifically, we first design a personalized self-training (PeST) strategy for unsupervised scenarios, which enables our model to capture precise community-level personalized information in a graph. With the benefit of the PeST, we alleviate class collision and unfairness without sacrificing the overall model performance. Furthermore, the aligned graph clustering (AlGC) is employed to obtain the community partition. In this module, we align the clustering space of our downstream task with that in PeST to achieve more consistent node embeddings. Finally, we demonstrate the effectiveness of our model for community detection both theoretically and experimentally. Extensive experimental results also show that our CEGCL exhibits state-of-the-art performance on three benchmark datasets with different scales.
