Factorized Orthogonal Latent Spaces

Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent spaces). However, in real scenarios, these assumptions are almost never truly satisfied. Recently, two methods have attempted to tackle this problem by factorizing the information and learn separate latent spaces for modeling the shared (i.e., correlated) and private (i.e., independent) parts of the data. However, these approaches are very sensitive to parameters setting or initialization. In this paper we propose a robust approach to factorizing the latent space into shared and private spaces by introducing orthogonality constraints, which penalize redundant latent representations. Furthermore, unlike previous approaches, we simultaneously learn the structure and dimensionality of the latent spaces by relying on a regularizer that encourages the latent space of each data stream to be low dimensional. To demo...

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Mathieu Salzmann, Carl Henrik Ek, Raquel Urtasun, Trevor Darrell
• Keywords: JMLR 2010, Latent Space, Redundant Latent Representations, Separate Latent Spaces