Multi-view least squares support vector classifiers with the principles of complementarity and consensus

Abstract

In this paper, we examine the multi-view learning framework, which adheres to the principles of complementarity and consensus. Despite significant advances in various support vector machine (SVM)-based multi-view learning methods, many focus exclusively on one of these principles. To bridge this gap, we first introduce the multi-view least squares support vector classifier (MvLSSVC-2C), which effectively minimizes the squares of the differences in decision functions across diverse views while also integrating information from multiple views through a coupling term. Furthermore, we propose a structural information-based model, termed SMvLSSVC-2C, which leverages hierarchical agglomerative clustering to enhance information exchange among views, thereby promoting complementarity and consensus. Meanwhile, by incorporating a weight allocation strategy, adaptive learning is conducted, and the importance of each view is adjusted to adhere to the principle of complementarity. We adopt the alternating optimization method to solve it. The two proposed methods exhibit superior performance, which is demonstrated by theoretical and numerical analysis. Our experimental results demonstrate the effectiveness of the proposed models on diverse datasets, highlighting their enhanced performance in multi-view learning tasks.