DWCL: Dual-Weighted Contrastive Learning for robust multi-view clustering

Multi-view contrastive clustering (MVCC) aims to learn consistent clustering structures from multiple views by maximizing the agreement between view-specific representations. However, existing methods often construct all pairwise cross-views indiscriminately, leading to numerous unreliable view combinations and representation degeneration. To address these issues, we propose Dual-Weighted Contrastive Learning (DWCL), a novel framework that selects the most reliable view using the silhouette coefficient and constructs targeted cross-views with other views via a Best-Other (B-O) contrastive mechanism. This strategy reduces the number of cross-views from quadratic to linear complexity, significantly improving computational efficiency. Additionally, we introduce a dual-weighting strategy that combines a view quality weight and a view discrepancy weight to adaptively emphasize high-quality, low-discrepancy cross-views. Extensive experiments on eight multi-view datasets demonstrate that DWCL consistently outperforms state-of-the-art methods. Specifically, DWCL achieves an absolute accuracy improvement of 3.5% on Caltech5V7 and 4.4% on CIFAR10. Theoretical analysis further validates the advantages of DWCL in improving mutual information bounds and reducing the influence of low-quality views. These results confirm that DWCL is a robust and efficient solution for scalable multi-view clustering.