Evolutionary Multi-task Optimization with Adaptive Knowledge Transfer

Evolutionary multi-task optimization (EMTO) studies how to simultaneously solve multiple optimization tasks via evolutionary algorithms (EAs) while making the useful knowledge acquired from solving one task to assist solving other tasks, aiming to improve the overall performance of solving each individual task. Recent years have seen a large body of EMTO works based on different kinds of EAs and studying one or more aspects in how to represent, extract, transfer and reuse knowledge. A key challenge to EMTO is the occurrence of negative knowledge transfer between tasks, which becomes severer when the total number of tasks increases. To address this issue, we propose an adaptive evolutionary multi-task optimization (AEMTO) framework. This framework can adapt knowledge transfer frequency, knowledge source selection and knowledge transfer intensity in a synergistic way to make best use of knowledge transfer especially when facing many tasks. We implement the proposed AEMTO framework and evaluate our implementation on three suites of MTO problems with two, 10 and 50 tasks and one real-world MTO problem with 2000 tasks in comparison to several state-of-the-art EMTO methods with certain adaptation strategies regarding knowledge transfer and the single-task optimization counterpart of the proposed method. Experimental results have demonstrated the effectiveness of the adaptive knowledge transfer strategies used in AEMTO and the overall performance superiority of AEMTO.