Incomplete Multi-View Representation Learning Through Anchor Graph-Based GCN and Information Bottleneck

Real-world data often contain incomplete views with varying degrees of missing information. While there are existing methods for learning representations from such data, effectively utilizing all incomplete view data and ensuring robustness to different levels of completeness remains a challenging task. To address this problem, we propose a novel framework named IMRL-AGI. IMRL-AGI combines the anchor graph-based Graph Convolutional Network (GCN) and information bottleneck. Specifically, the framework starts by constructing an anchor graph to effectively captures the nonlinear information between instances. Next, an anchor graph-based GCN is designed to extract feature information from various views. IMRL-AGI maximizes the mutual information between the views obtained by the common representation and the anchor-graph-based GCN, ensuring the accurate extraction of view information. Furthermore, the minimization of mutual information is applied to promote diversity and reduce redundancy in the multi-view representation. Extensive experiments are conducted on several real-world datasets, and the results demonstrate the superiority of IMRL-AGI.

1. INTRODUCTION

In the era of big data, the presence of multiple modalities in data is prevalent [1], [2], [3], [4]. However, it is common for data to be missing during the data collection process [5]. As depicted in Fig. 1(a) and Fig. 1(b), two common types of missing data patterns can be observed [6], [7], [8]. One type is charac-terized by many instances containing all views, while some instances have only one view. The other type involves randomly missing views. Therefore, a number of algorithms for incomplete multiview representation learning (IMRL) have been proposed to learn consistent representations in the presence of missing views [9], [10].