Abstract:
Standard classification models are usually additive models, which only consider the contributions from the main effects of features. When the features are highly correlat...Show MoreMetadata
Abstract:
Standard classification models are usually additive models, which only consider the contributions from the main effects of features. When the features are highly correlated, the interactions between features provide us not only more additional features, but also the underlying graphs between features. In this paper, we integrate into multiclass SVM a strong hierarchy regularization in order to learn the main effects and the interactions. A primal-dual proximal algorithm with epigraphical projection is proposed to minimize the objective function. The proposed algorithm is applied to face classification task on the Extended YaleB database and the results validate its effectiveness.
Published in: 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)
Date of Conference: 17-20 September 2018
Date Added to IEEE Xplore: 01 November 2018
ISBN Information:
Print on Demand(PoD) ISSN: 1551-2541