Relationship completion for incomplete multi-view clustering

In real-world scenarios, multi-view data usually contain missing or incomplete samples due to factors such as technical limitations and privacy issues during data collection or transmission. To alleviate this problem, Incomplete Multi-View Clustering (IMVC) has attracted increasing attention. Most existing IMVC methods still suffer from the following problems: (1) They do not make full use of structural relationship information of multi-view data to deal with missing values; (2) They face the challenge of maintaining the integrity of the original data and effectively avoiding error propagation when dealing with missing data; (3) They excel at deriving shared representations across multiple views but often overlook the uncertainty in clustering assignments within each view, resulting in increased category ambiguity. To address these issues, we propose a novel method, Relationship Completion for Incomplete Multi-View Clustering. Specifically, we design a novel relationship completion module to solve the missing value problem and obtain excellent relation graph features by directly completing the relationships of the missing views, ensuring the integrity of the original data and effectively mitigating the errors introduced during the completion process. We exploit multi-view complementary information through attention layer fusion and high-confidence bootstrapping. Semantic contrast learning and multi-view label distribution learning are introduced to further exploit multi-view consistent information. Extensive experiments with state-of-the-art methods on multiple real datasets demonstrate the effectiveness and superiority of the proposed method.