Multi-Task Optimization and Multi-Task Evolutionary Computation in the Past Five Years: A Brief Review

Abstract

Traditional evolution algorithms tend to start the search from scratch. However, real-world problems seldom exist in isolation and humans effectively manage and execute multiple tasks at the same time. Inspired by this concept, the paradigm of multi-task evolutionary computation (MTEC) has recently emerged as an effective means of facilitating implicit or explicit knowledge transfer across optimization tasks, thereby potentially accelerating convergence and improving the quality of solutions for multi-task optimization problems. An increasing number of works have thus been proposed since 2016. The authors collect the abundant specialized literature related to this novel optimization paradigm that was published in the past five years. The quantity of papers, the nationality of authors, and the important professional publications are analyzed by a statistical method. As a survey on state-of-the-art of research on this topic, this review article covers basic concepts, theoretical foundation, basic implementation approaches of MTEC, related extension issues of MTEC, and typical application fields in science and engineering. In particular, several approaches of chromosome encoding and decoding, intro-population reproduction, inter-population reproduction, and evaluation and selection are reviewed when developing an effective MTEC algorithm. A number of open challenges to date, along with promising directions that can be undertaken to help move it forward in the future, are also discussed according to the current state. The principal purpose is to provide a comprehensive review and examination of MTEC for researchers in this community, as well as promote more practitioners working in the related fields to be involved in this fascinating territory.

Evolutionary Multitask Optimization: Fundamental research questions, practices, and directions for the future

“…After years of activity that have been summarized in recent surveys on Evolutionary Multitasking [7,8], we firmly believe that it is the moment to expose and reflect these crucial concerns. Solid and informed answers to these fundamental questions are still lacking, which can lead to undesirable developments and outcomes of no practical value in the future of this field.…”

“…For further information about how algorithmic schemes based on these two strategies work, we refer our readers to comprehensive surveys recently published in [7,8,11,12]. Among them, MFEA [10] and MFEA-II [13] stand out as the arguably most influential works in the field.…”

“…An upsurge of contributions has been noted around Evolutionary Multitasking and related concepts, as has been made clear in recent survey papers around the topic [7,8]. However, some fundamental questions need still to be clarified.…”

“…We firmly advocate for studies in which the connections of newly proposed algorithms to traditional areas of optimization research are identified, so that ambiguities are minimized, and meaningful advances are achieved. In this regard, a remarkable attempt is made in the survey published in [8] to describe the theoretical foundations of evolutionary multitask optimization, examining its mathematical ingredients and clearly defining each mechanism and solving strategy. More along this line, in [7], the main concepts of multitasking optimization are differentiated from other potentially colliding fields, such as multi-objective optimization or transfer learning.…”

Machine learning applications in river research: Trends, opportunities and challenges

“…In a comparison between Pareto optimisation and single‐objective optimisation of species distribution models for river management by Gobeyn and Goethals (2019), the Pareto approach was two to four times more efficient in identifying a wide‐range set of optimal models with only a 4% increase in runtime compared to the latter optimisation. Note that unlike multi‐objective optimisation, multi‐task optimisation aims to find the optimal solutions for multiple tasks in a single simulation (Xu et al, 2021). For example, instead of applying numerous models to predict single water quality variable, Zhang et al (2019) applied a multi‐task temporal convolution network to forecast various water quality constituents simultaneously, leading to a significantly reduced training time while retaining a promising predictive accuracy.…”