Matthias Dorfer, Gerhard Widmer,
"Towards Deep and Discriminative Canonical Correlation Analysis"
: ICML 2016 Workshop on Multi-View Representation Learning, 6-2016
Towards Deep and Discriminative Canonical Correlation Analysis
Sprache des Titels:
ICML 2016 Workshop on Multi-View Representation Learning
We introduce a discriminative extension of Deep
Canonical Correlation Analysis (DCCA) for the
purpose of multi-view representation learning.
The objective of DCCA is to learn two groups of
latent features which are highly correlated when
projected into the common CCA-space. Repre-
sentations learned with DCCA pre-training have
proven to be beneficial when used in a subse-
quent classification tasks. In this work we tackle
exactly the problem of multi-view classification
by incorporating a discriminative regularizer on
the hidden representations already at train time.
Inspired by a deep learning interpretation of Lin-
ear Discriminant Analysis (DeepLDA) we de-
sign a joint optimization target that encourages
the network to learn representations which are
not only correlated but also highly discrimina-
tive. Preliminary results show that the joint opti-
mization of correlation and separation is feasible
and helps to enhance the classification power of
the learned representations.