Multi-kernel maximum entropy discrimination for multi-view learning

Article type: Research Article

Authors: Chao, Guoqing | Sun, Shiliang^*

Affiliations: Shanghai Key Laboratory of Multidimensional Information Processing, Department of Computer Science and Technology, East China Normal University, Shanghai, China

Correspondence: [*] Corresponding author: Shiliang Sun, Shanghai Key Laboratory of Multidimensional Information Processing, Department of Computer Science and Technology, East China Normal University, 500 Dongchuan Road, Shanghai 200241, China. Tel.: +86 21 54345183; Fax: +86 21 54345119; E-mail:slsun@cs.ecnu.edu.cn

Abstract: Maximum entropy discrimination (MED) is a general framework for discriminative estimation which integrates the principles of maximum entropy and maximum margin. In this paper, we propose a novel approach named multi-kernel MED (MKMED) for multi-view learning (MVL), which takes advantage of the complementary principle for MVL. Multiple kernels encode the similarities in different views. We obtain a kernel matrix by multiple kernel combination to make use of the complementary information in different views. Based on the kernel matrix obtained by multiple kernel combination, we can proceed MVL within the MED framework. The experimental results on multiple datasets demonstrate the effectiveness of the proposed MKMED. MKMED outperforms the single-view MEDs and a competing MVL mothod named SVM-2K, and is competitive with the state-of-the-art multi-view MED (MVMED) and even sometimes exceeds it.

Keywords: Multi-view learning, maximum entropy discrimination, multi-kernel learning

DOI: 10.3233/IDA-160816

Journal: Intelligent Data Analysis, vol. 20, no. 3, pp. 481-493, 2016