.png){kind=icon}
Return
Survey on multi-task optimization: Towards cross-domain and asynchronous multi-task
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2025.102175.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Journal
IF:
8.5
Papers:
2.2K
Citations:
1.0W
Organization
Cited Papers
No cited papers available