Incomplete Multi-View Clustering Based on Joint Concept Decomposition and Anchor Graph Learning

EasyChair Preprint 15922

Abstract

The main objective of incomplete multi-view clustering is to effectively utilize the existing view information to fill in the missing data and to mine the complementary information and potential associations between multiple views to effectively group samples. The existing primary means for recovering missing information are classified into two parts: one uses matrix decomposition or low-rank constraints to fill in the missing views, and the other constructs multiple graph structures and uses graph regularization to recover the corresponding missing parts. However, the two methods are relatively independent and are not used jointly to improve the model performance. This paper proposes an incomplete multi-view clustering method with complete clustering metrics and complete anchor graphs (CFAG). Specifically, each view's missing samples are recovered by a matrix of consistent clustering metrics and represented by an anchor graph. The recovered complete data performs anchor graph construction and anchor learning and utilizes the orthogonal variation principle to learn the consistency structure of multiple anchor graphs to mine the complementary information among multiple views. The clustering metrics are obtained based on the consistency structure, and the consistency of the clustering metrics is also considered to obtain the final clustering results. The effectiveness of the proposed method is verified on multiple datasets.

Keyphrases: Anchor graph, Missing views recovery, incomplete multi-view clustering

@booklet{EasyChair:15922,
  author    = {Zhuowen Li and Hongmei Chen and Biao Xiang and Zhong Yuan and Chuan Luo and Tianrui Li},
  title     = {Incomplete Multi-View Clustering Based on Joint Concept Decomposition and Anchor Graph Learning},
  howpublished = {EasyChair Preprint 15922},
  year      = {EasyChair, 2025}}