Two view learning: SVM-2K, Theory and Practice
Jason Farquhar, David Hardoon, Hongying Meng, John Shawe-Taylor and Sandor Szedmak
In: NIPS 2005, 5 Dec - 8 Dec 2005, Vancouver.
Kernel methods make it relatively easy to define complex
high-dimensional feature spaces. This raises the question of how
we can identify the relevant subspaces for a particular learning
task. When two views of the same phenomenon are available kernel
Canonical Correlation Analysis (KCCA) has been shown to be an
effective preprocessing step that can improve the performance of
classification algorithms such as the Support Vector Machine
(SVM). This paper takes this observation to its logical conclusion
and proposes a method that combines this two stage learning (KCCA
followed by SVM) into a single optimisation termed SVM-2K. We
present both experimental and theoretical analysis of the approach
showing encouraging results and insights.