Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
This work addresses limitations in unsupervised deep graph clustering for complex real data, representing an incremental improvement over existing graph contrastive learning models.
The paper tackled the challenges of noise from random graph augmentation and inflexible sample selection in graph contrastive learning by proposing the CCGL framework, which uses clustering entropy to guide augmentation and a multi-task curriculum learning scheme, achieving excellent performance compared to state-of-the-art methods.
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.