Deep Incomplete Multi-View Clustering Based on Subspace Learning
Jiao Wang1,*, Tingting Song2,*, Yunhui Zhou1
1 School of Information and Control Engineering, Southwest University of Science and Technology, Mianyang, China
2 Health Electronics Center, Institute of Microelectronics of Chinese Academy of Sciences, Beijing, China
* Corresponding Author: Jiao Wang. Email: 
; Tingting Song. Email: 
(This article belongs to the Special Issue: AI-Driven Image Processing and Pattern Recognition: Advances in Algorithms, Models, and Applications)
Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.087751
Received 22 June 2026; Accepted 30 July 2026; Published online 17 September 2026
Abstract
In practical scenarios, multi-view data often contains missing entries caused by complicated data collection and transmission procedures, posing great challenges to clustering analysis. Existing incomplete multi-view clustering methods have two obvious limitations: (1) Imputation-based methods inevitably generate inaccurate information during data recovery; (2) Imputation-free methods struggle to balance cross-view consistency and complementarity. To tackle the above issues, this paper proposes a deep incomplete multi-view clustering approach based on subspace learning, which integrates latent feature extraction, K-nearest neighbor-based feature imputation, cross-view contrastive alignment, and attention-driven fusion within a unified deep learning framework. Specifically, we first leverage autoencoders to extract view-specific latent features. Inspired by the observation that different views of the same sample should share similar latent representations, we impute missing latent features by leveraging cross-view correlations, using both view-specific complete features and common complete features through the K-nearest neighbor strategy. Then, we construct a fully-connected neural network layer to learn the self-expression matrix for each view. To minimize the impact of imputation noise on learning the self-expression matrix for clustering, these self-expression matrices are enforced to align using contrastive learning to capture cross-view consistency, and then fused based on a channel attention mechanism for pursuing cross-view complementarity. Finally, a high-quality cross-view consensus self-expression matrix is obtained for final clustering segmentation. Comprehensive evaluations on six benchmark datasets under various missing rates demonstrate the effectiveness and superiority of our method compared with state-of-the-art methods.
Keywords
Deep incomplete multi-view clustering; subspace learning; missing feature imputation; contrastive alignment; attentive fusion
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
