Partial Multi-view Clustering via Consistent GAN

Multi-view clustering, as one of the most important methods to analyze multi-view data, has been widely used in many real-world applications. Most existing multi-view clustering methods perform well on the assumption that each sample appears in all views. Nevertheless, in real-world application, each view may well face the problem of the missing data due to noise, or malfunction. In this paper, a new consistent generative adversarial network is proposed for partial multi-view clustering. We learn a common low-dimensional representation, which can both generate the missing view data and capture a better common structure from partial multi-view data for clustering. Different from the most existing methods, we use the common representation encoded by one view to generate the missing data of the corresponding view by generative adversarial networks, then we use the encoder and clustering networks. This is intuitive and meaningful because encoding common representation and generating the missing data in our model will promote mutually. Experimental results on three different multi-view databases illustrate the superiority of the proposed method.

I. Introduction

Nowadays, with the advance of hardware technology, multi-view data, which are come from different sources for one subject, are common in real-world [1], [2]. For example, one image can be represented either by visual feature or text annotation. In general, different views provide complementary information to describe the data, which lets multi-view learning achieve promising performance, and draws research efforts in many fields such as data analysis, image classification, multimedia and information retrieval [3], [4].