Correlational Neural Networks
This work addresses the challenge of scalable and effective multi-view representation learning, particularly for cross-language applications, though it is incremental as it combines elements of existing paradigms.
The authors tackled the problem of learning common representations from multiple data views by proposing Correlational Neural Network (CorrNet), an autoencoder-based method that explicitly maximizes correlation in the common subspace, and demonstrated it outperforms existing approaches like CCA and standard autoencoders in learning correlated representations and cross-language tasks.
Common Representation Learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, is receiving a lot of attention recently. Two popular paradigms here are Canonical Correlation Analysis (CCA) based approaches and Autoencoder (AE) based approaches. CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA based approaches outperform AE based approaches for the task of transfer learning, they are not as scalable as the latter. In this work we propose an AE based approach called Correlational Neural Network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than the above mentioned approaches with respect to its ability to learn correlated common representations. Further, we employ CorrNet for several cross language tasks and show that the representations learned using CorrNet perform better than the ones learned using other state of the art approaches.