Incomplete Multi-View Clustering With Complete View Guidance

In recent years, multi-view clustering has gained widespread attention in signal processing because multi-view data contains more information than a single view. However, multi-view data is often incomplete due to missing data in one or more random views. Therefore, several methods have been proposed for incomplete multi-view clustering to learn features that contain consensus information for clustering incomplete multi-view data (IMD). However, there is a part of the IMD that is not missing in any view, and most previous methods have not utilized this part to guide the process of learning consensus information. To address this issue, we design a knowledge distillation framework for incomplete multi-view clustering and propose an incomplete multi-view clustering with complete view guidance (IMC-CVG). We first train a robust teacher model with contrastive learning loss on the complete part of IMD to learn consensus features containing multi-view information. Then, we train a student model on all the IMD, where we mask partial views of the complete data to simulate missing data, and utilize the teacher model to guide the student model to learn consensus features that contain as much multi-view information as possible. Experiments show that our proposed method outperforms all the compared state-of-the-art methods.

I. Introduction

With the signal acquisition technology development, multi-view data has become increasingly popular in signal processing, and has been used to describe various things [1], [2], [3]. For example, in [4], different physiological signals such as Electroencephalography, Electrooculography, and Electromyogram are employed to classify sleep stages. Many experiments [5], [6], [7] have demonstrated that using multi-view methods can significantly improve the effectiveness of analytical approaches. This is because multi-view data can provide more information than a single view [8], [9], [10], [11]. However, multi-view data is often incomplete in reality, due to a part of the data missing on the random view caused by some unexpected reasons such as manual omission or equipment trouble. The challenge of learning multi-view information from incomplete multi-view data (IMD) often results in the failure of traditional multi-view clustering methods [11].