Multi-Task Multi-View Learning Based on Cooperative Multi-Objective Optimization

Abstract

Traditional multi-task multi-view (MTMV) models work under the single-objective learning framework and cannot incorporate too many regularization terms, which are primarily attributed to the utilization of the conventional numerical optimization methods. To this end, a cooperative multi-objective MTMV (CMO-MTMV) learning method is proposed in this paper. In CMO-MTMV, the MTMV problem is formulated as a multi-objective optimization problem. Compared with the existing single-objective MTMV learning methods, the proposed CMO-MTMV method integrates more relations, including task–task, view–view, instance–instance, and feature–feature relations as multiple objectives. An effective cooperative multi-objective quantum-behaved particle swarm optimization (CMOQPSO) algorithm is further developed to solve the multi-objective optimization problem. The integration of a multi-swarm scheme and a local communication strategy in CMOQPSO renders this algorithm efficient. The experimental results verify the superiority of the proposed CMO-MTMV method compared with the several state-of-the-art machine-learning methods.