Abstract
Multi-view clustering (MVC) has emerged as a powerful tool for analyzing complex datasets by leveraging consistent and complementary information from multiple sources. However, MVC faces three critical challenges in real-world scenarios: (1) Sample-level misalignment due to unknown cross-view correspondence, which introduces noisy correlations, (2) Feature-level heterogeneity from divergent dimensional spaces across views obscuring shared discriminative patterns, and (3) Dynamic-view inefficiency when integrating sequentially arriving data under privacy or sensor constraints. These challenges collectively hinder the clustering performance of existing studies, thus giving rise to a unified framework. To bridge this gap, we propose ASIA-MVC, an anchor-guided sample-and-feature incremental alignment framework for MVC, which is the first attempt in incremental learning on sample-unpaired multi-view data. First, the sample alignment module dynamically maps unpaired samples across views via anchor-based bipartite graphs. Second, the feature-aligned module employs an orthogonal decomposition strategy to unify heterogeneous feature spaces while preserving discriminative structures. Third, the novel incremental fusion framework integrates the dual-aligned modules under the guidance of shared anchors, enabling efficient cross-view representation learning. Furthermore, to solve the resulting problem, we develop a novel three-step alternate optimization algorithm with guaranteed convergence. Finally, the proposed method is validated in extensive experiments and achieves leading cluster efficiency and an outstanding sample-aligned effect.
Funding Information
  • National Science and Technology Innovation 2030 Major Project of China (2022ZD0209103)
  • National Natural Science Foundation of China (62476281)
  • National Natural Science Foundation of China (62306324)
  • National Natural Science Foundation of China (62376279)
  • National Natural Science Foundation of China Joint Found (U24A20323 and U24A20333)
  • science and technology innovation Program of Hunan Province (2024RC3128)
  • National University of Defense Technology Research Foundation (ZK24-30)

This publication has 52 references indexed in Scilit: