Survey on multi-task optimization: Towards cross-domain and asynchronous multi-task

IF 8.5 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Swarm and Evolutionary Computation Pub Date : 2025-09-29 DOI:10.1016/j.swevo.2025.102175

Honggui Han , Ben Zhao , Xiaolong Wu , Xin Li

{"title":"Survey on multi-task optimization: Towards cross-domain and asynchronous multi-task","authors":"Honggui Han , Ben Zhao , Xiaolong Wu , Xin Li","doi":"10.1016/j.swevo.2025.102175","DOIUrl":null,"url":null,"abstract":"<div><div>Multi-task optimization (MTO) accelerates the acquisition of optimal solutions for all tasks through effective knowledge transfer. To satisfy various practical demands, multiple tasks are often transformed into different types of optimization problems. Hence, there are numerous MTO variants in the MTO research community. To motivate deeper research on MTO and its variants, this paper mainly summarizes MTO and its variants from single-domain to cross-domain and from synchronous to asynchronous. First, the single-domain and synchronous MTO is classified into single-objective MTO, multi-objective MTO, constrained MTO, many-task optimization, and other variants based on the task types. Second, technical applications that employ MTO techniques to solve other types of optimization problems are also collated, which differ significantly from MTO variants. Finally, several promising research directions of MTO are presented theoretically and practically, including mining knowledge representations to minimize information loss, cross-domain MTO with multiple different task types, asynchronous MTO with inconsistent task arrival times, and an application of MTO to neural architecture search problems.</div></div>","PeriodicalId":48682,"journal":{"name":"Swarm and Evolutionary Computation","volume":"99 ","pages":"Article 102175"},"PeriodicalIF":8.5000,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Swarm and Evolutionary Computation","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2210650225003323","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

Multi-task optimization (MTO) accelerates the acquisition of optimal solutions for all tasks through effective knowledge transfer. To satisfy various practical demands, multiple tasks are often transformed into different types of optimization problems. Hence, there are numerous MTO variants in the MTO research community. To motivate deeper research on MTO and its variants, this paper mainly summarizes MTO and its variants from single-domain to cross-domain and from synchronous to asynchronous. First, the single-domain and synchronous MTO is classified into single-objective MTO, multi-objective MTO, constrained MTO, many-task optimization, and other variants based on the task types. Second, technical applications that employ MTO techniques to solve other types of optimization problems are also collated, which differ significantly from MTO variants. Finally, several promising research directions of MTO are presented theoretically and practically, including mining knowledge representations to minimize information loss, cross-domain MTO with multiple different task types, asynchronous MTO with inconsistent task arrival times, and an application of MTO to neural architecture search problems.

查看原文本刊更多论文

多任务优化研究综述：面向跨域、异步多任务

多任务优化（MTO）通过有效的知识转移加速了对所有任务的最优解的获取。为了满足各种实际需求，往往会将多个任务转化为不同类型的优化问题。因此，在MTO研究社区中有许多MTO变体。为了激发对MTO及其变体的深入研究，本文主要对MTO及其变体从单域到跨域、从同步到异步进行了总结。首先，根据任务类型将单域同步MTO分为单目标MTO、多目标MTO、约束MTO、多任务优化和其他变体。其次，还整理了采用MTO技术解决其他类型优化问题的技术应用，这与MTO变体有很大不同。最后，从理论和实践两方面提出了MTO的研究方向，包括挖掘知识表示最小化信息丢失、多任务类型跨域MTO、任务到达时间不一致的异步MTO以及MTO在神经结构搜索问题中的应用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Swarm and Evolutionary Computation COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCEC-COMPUTER SCIENCE, THEORY & METHODS

CiteScore

16.00

自引率

12.00%

发文量

169

期刊介绍： Swarm and Evolutionary Computation is a pioneering peer-reviewed journal focused on the latest research and advancements in nature-inspired intelligent computation using swarm and evolutionary algorithms. It covers theoretical, experimental, and practical aspects of these paradigms and their hybrids, promoting interdisciplinary research. The journal prioritizes the publication of high-quality, original articles that push the boundaries of evolutionary computation and swarm intelligence. Additionally, it welcomes survey papers on current topics and novel applications. Topics of interest include but are not limited to: Genetic Algorithms, and Genetic Programming, Evolution Strategies, and Evolutionary Programming, Differential Evolution, Artificial Immune Systems, Particle Swarms, Ant Colony, Bacterial Foraging, Artificial Bees, Fireflies Algorithm, Harmony Search, Artificial Life, Digital Organisms, Estimation of Distribution Algorithms, Stochastic Diffusion Search, Quantum Computing, Nano Computing, Membrane Computing, Human-centric Computing, Hybridization of Algorithms, Memetic Computing, Autonomic Computing, Self-organizing systems, Combinatorial, Discrete, Binary, Constrained, Multi-objective, Multi-modal, Dynamic, and Large-scale Optimization.