Multi-View Representation Learning: A Survey from Shallow Methods to Deep Methods
share
Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces several principles for multi-view representation learning: correlation, consensus, and complementarity principles. Consequently, we first review the representative methods and theories of multi-view representation learning based on correlation principle, especially on canonical correlation analysis (CCA) and its several extensions. Then from the viewpoint of consensus and complementarity principles we investigate the advancement of multi-view representation learning that ranges from shallow methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to deep methods including multi-modal restricted Boltzmann machines, multi-modal autoencoders, and multi-modal recurrent neural networks. Further, we also provide an important perspective from manifold alignment for multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical basis and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.
READ FULL TEXT