Deep Variational Canonical Correlation Analysis
arXiv:1610.03454
Abstract
We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA to nonlinear observation models parameterized by deep neural networks. We derive variational lower bounds of the data likelihood by parameterizing the posterior probability of the latent variables from the view that is available at test time. We also propose a variant of VCCA called VCCA-private that can, in addition to the "common variables" underlying both views, extract the "private variables" within each view, and disentangles the shared and private information for multi-view data without hard supervision. Experimental results on real-world datasets show that our methods are competitive across domains.
References in corpus (2)
Cited by in corpus (15)
- Learning Robust Representations via Multi-View Information Bottleneck
- Trusted Multi-View Classification
- Multimodal Generative Models for Compositional Representation Learning
- Disentangled Cumulants Help Successor Representations Transfer to New Tasks
- Variational Deep Semantic Hashing for Text Documents
- Shared Generative Latent Representation Learning for Multi-view Clustering
- Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
- Deep Tensor CCA for Multi-view Learning
- Deep Co-Attention Network for Multi-View Subspace Learning
- Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis
- A Generative Map for Image-based Camera Localization
- Disentangled Variational Information Bottleneck for Multiview Representation Learning
- Adversarial Canonical Correlation Analysis
- Multi-view Alignment and Generation in CCA via Consistent Latent Encoding
- Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach