Deep Contrastive Multi-view Clustering under Semantic Feature Guidance
This work addresses a specific bottleneck in multi-view clustering for researchers, but it is incremental as it builds on existing contrastive learning approaches.
The paper tackled the problem of false negative pairs in contrastive learning for multi-view clustering by proposing a framework that uses semantic feature guidance to weaken contrastive learning between such pairs, resulting in outperforming state-of-the-art methods on several public datasets.
Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting the performance of existing algorithms from further improvement. To solve this problem, we propose a multi-view clustering framework named Deep Contrastive Multi-view Clustering under Semantic feature guidance (DCMCS) to alleviate the influence of false negative pairs. Specifically, view-specific features are firstly extracted from raw features and fused to obtain fusion view features according to view importance. To mitigate the interference of view-private information, specific view and fusion view semantic features are learned by cluster-level contrastive learning and concatenated to measure the semantic similarity of instances. By minimizing instance-level contrastive loss weighted by semantic similarity, DCMCS adaptively weakens contrastive leaning between false negative pairs. Experimental results on several public datasets demonstrate the proposed framework outperforms the state-of-the-art methods.