One-Class Classification Using <i>l_p</i>-Norm Multiple Kernel Fisher Null Approach

We address the one-class classification (OCC) prob-lem and advocate a one-class MKL (multiple kernel learning) approach for this purpose. To this aim, based on the Fisher null-space OCC principle, we present a multiple kernel learning algorithm where an l(p)-norm regularisation (p =1) is considered for kernel weight learning. We cast the proposed one-class MKL problem as a min-max saddle point Lagrangian optimisation task and propose an efficient approach to optimise it. An extension of the proposed approach is also considered where several related one-class MKL tasks are learned concurrently by constraining them to share common weights for kernels. An extensive eval-uation of the proposed MKL approach on a range of data sets from different application domains confirms its merits against the baseline and several other algorithms.