Deep Multi-View Learning via Task-Optimal CCA
This work addresses multi-view learning for researchers and practitioners by providing a more effective approach, though it appears incremental as it builds on existing CCA methods.
The paper tackled the problem of multi-view learning by developing a method that simultaneously optimizes CCA and task objectives end-to-end, resulting in a non-linear projection that improves cross-view classification, regularization, and semi-supervised learning on real data, with significant gains over previous state-of-the-art.
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use of class labels. Recent CCA methods have started to address this weakness but are limited in that they do not simultaneously optimize the CCA projection for discrimination and the CCA projection itself, or they are linear only. We address these deficiencies by simultaneously optimizing a CCA-based and a task objective in an end-to-end manner. Together, these two objectives learn a non-linear CCA projection to a shared latent space that is highly correlated and discriminative. Our method shows a significant improvement over previous state-of-the-art (including deep supervised approaches) for cross-view classification, regularization with a second view, and semi-supervised learning on real data.