Deep Tensor CCA for Multi-View Learning

Hok Shing WONG, Li WANG*, Raymond CHAN, Tieyong ZENG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

12 Citations (Scopus)


We present Deep Tensor Canonical Correlation Analysis (DTCCA), a method to learn complex nonlinear transformations of multiple views (more than two) of data such that the resulting representations are linearly correlated in high order. The high-order correlation of given multiple views is modeled by covariance tensor, which is different from most CCA formulations relying solely on the pairwise correlations. Parameters of transformations of each view are jointly learned by maximizing the high-order canonical correlation. To solve the resulting problem, we reformulate it as the best sum of rank-1 approximation, which can be efficiently solved by existing tensor decomposition method. DTCCA is a nonlinear extension of tensor CCA (TCCA) via deep networks. Comparing with kernel TCCA, DTCCA not only can deal with arbitrary dimensions of the input data, but also does not need to maintain the training data for computing representations of any given data point. Hence, DTCCA as a unified model can efficiently overcome the scalable issue of TCCA for either high-dimensional multi-view data or a large amount of views, and it also naturally extends TCCA for learning nonlinear representation. Extensive experiments on four multi-view data sets demonstrate the effectiveness of the proposed method.

Original languageEnglish
Pages (from-to)1664-1677
Number of pages14
JournalIEEE Transactions on Big Data
Issue number6
Publication statusPublished - 1 Dec 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2015 IEEE.


  • canonical correlation analysis
  • deep networks
  • Multi-view learning
  • tensor decomposition


Dive into the research topics of 'Deep Tensor CCA for Multi-View Learning'. Together they form a unique fingerprint.

Cite this