CDMVC: Consensus-Driven Multiview Clustering via Adaptive Hierarchical Matrix Factorization With Dynamic View Fusion

Multi-view clustering is important for discovering shared patterns from heterogeneous data, but many existing methods are constrained by fixed architectures, rigid fusion strategies, and weak theoretical support. We propose a new framework CDMVC, which integrates adaptive hierarchical matrix factorization with dynamic view fusion. First, an AHMD module is designed to automatically determine the decomposition depth of each view based on its intrinsic complexity, thus avoiding the limitations of manually specified or fixed-depth structures. Second, a consensus-driven fusion mechanism jointly preserves view-specific information and cross-view consistency through an adaptive optimization process with theoretical guarantees. Third, a dynamic weighting strategy updates the contribution of each view according to its structural quality and clustering relevance. Theoretical analysis proves the convergence of CDMVC, and experiments on benchmark datasets demonstrate that CDMVC consistently achieves superior clustering performance while maintaining computational efficiency.