<ul><li>Late Fusion Multi-View Clustering (LFMVC) aims to integrate complementary information from multiple views to enhance clustering performance.</li><li>Current LFMVC methods struggle with noisy and redundant partitions and often fail to capture high-order correlations across views.</li><li>A novel theoretical framework is presented for analyzing the generalization error bounds of multiple kernel k-means, leveraging local Rademacher complexity and principal eigenvalue proportions.</li><li>Experimental results on benchmark datasets confirm that the proposed approach outperforms state-of-the-art methods in clustering performance and robustness.</li></ul>

Sharper Error Bounds in Late Fusion Multi-view Clustering Using Eigenvalue Proportion

Discover more