Total: 1
In incomplete multi-view clustering (IMVC), missing data introduces noise, causing view prototypes to shift and exhibit inconsistent semantics across views. A feasible solution is to explore cross-view consistency in paired complete observations for imputation and alignment. However, existing paradigm is limited to instance- or cluster-level. The former emphasizes instances alignment across views, and wrongly regards unpaired observations with semantic consistency as negative pairs; the latter focuses on cluster counterparts across views but ignores intra-cluster observations within views. Neither can construct a semantic space shared for all view data to learn consensus semantic representation. Meanwhile, excessive reliance on consistency results in unreliable imputation and alignment without incorporating view-specific cluster information. To this end, we propose an IMVC framework, imputation- and alignment-free for consensus semantics learning (FreeCSL). For consensus semantics learning, a consensus prototypes, linearly weighted by all available data, is introduced to promote consensus assignments between paired observations in a shared semantic space, called as prototype-based contrastive clustering. For cluster semantics enhancement, we design a heuristic graph clustering based on modularity metric for specific view to recover cluster structure with intra-cluster compactness and inter-cluster separation. Extensive experiments demonstrate, compared to existing state-of-the-art competitors, FreeCSL is better at achieving confident and robust assignments on incomplete datasets.