Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance

TL;DR

This paper introduces CCGL, a novel graph contrastive learning framework that uses clustering entropy to guide data augmentation and adaptive sample selection, improving the capture of complex data structures.

Contribution

The paper proposes a clustering entropy-guided curriculum learning approach for graph contrastive learning, addressing limitations of existing methods in data augmentation and sample selection.

Findings

CCGL outperforms state-of-the-art methods in graph clustering tasks.

Adaptive sample selection improves model robustness on complex data.

Clustering-guided augmentation enhances semantic preservation.

Abstract

Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face challenges: 1) graph augmentation is used to improve learning diversity, but commonly used random augmentation methods may destroy inherent semantics and cause noise; 2) the fixed positive and negative sample selection strategy is limited to deal with complex real data, thereby impeding the model's capability to capture fine-grained patterns and relationships. To reduce these problems, we propose the Clustering-guided Curriculum Graph contrastive Learning (CCGL) framework. CCGL uses clustering entropy as the guidance of the following graph augmentation and contrastive learning. Specifically, according to the clustering entropy, the intra-class edges and important features are emphasized in augmentation. Then, a multi-task curriculum learning scheme is proposed, which employs the clustering guidance to shift the focus from the discrimination task to the clustering task. In this way, the sample selection strategy of contrastive learning can be adjusted adaptively from early to late stage, which enhances the model's flexibility for complex data structure. Experimental results demonstrate that CCGL has achieved excellent performance compared to state-of-the-art competitors.