基于聚类熵引导的多任务课程图对比学习
Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
AI总结：
针对图对比学习中随机增强破坏语义及固定样本选择策略难以处理复杂数据的问题，提出CCGL框架，利用聚类熵引导图增强与多任务课程学习，自适应调整样本选择策略，显著提升了无监督深度图聚类的性能。
摘要：
对比学习极大地推动了无监督深度图聚类的最新进展。尽管取得了长足进步，大多数图对比学习模型仍面临挑战：1）图增强用于提高学习多样性，但常用的随机增强方法可能破坏固有语义并引入噪声；2）固定的正负样本选择策略难以处理复杂的真实数据，从而阻碍模型捕捉细粒度模式与关系的能力。为减轻这些问题，我们提出了聚类引导课程图对比学习（CCGL）框架。CCGL利用聚类熵作为后续图增强和对比学习的指导。具体而言，根据聚类熵，增强过程会强调类内边缘和重要特征。随后，提出了一种多任务课程学习方案，该方案利用聚类指导将重点从判别任务转移到聚类任务。通过这种方式，对比学习的样本选择策略能够在早期到晚期阶段进行自适应调整，从而增强模型对复杂数据结构的灵活性。实验结果表明，与最先进的竞争方法相比，CCGL取得了卓越的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
