Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997646596> ?p ?o ?g. }
- W2997646596 abstract "Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization. In this paper, we generalize this idea and propose a novel Pareto multi-task learning algorithm (Pareto MTL) to find a set of well-distributed Pareto solutions which can represent different trade-offs among different tasks. The proposed algorithm first formulates a multi-task learning problem as a multiobjective optimization problem, and then decomposes the multiobjective optimization problem into a set of constrained subproblems with different trade-off preferences. By solving these subproblems in parallel, Pareto MTL can find a set of well-representative Pareto optimal solutions with different trade-off among all tasks. Practitioners can easily select their preferred solution from these Pareto solutions, or use different trade-off solutions for different situations. Experimental results confirm that the proposed algorithm can generate well-representative solutions and outperform some state-of-the-art algorithms on many multi-task learning applications." @default.
- W2997646596 created "2020-01-10" @default.
- W2997646596 creator A5000546219 @default.
- W2997646596 creator A5008386708 @default.
- W2997646596 creator A5024948361 @default.
- W2997646596 creator A5031170152 @default.
- W2997646596 creator A5068670330 @default.
- W2997646596 date "2019-12-30" @default.
- W2997646596 modified "2023-09-25" @default.
- W2997646596 title "Pareto Multi-Task Learning" @default.
- W2997646596 cites W1559060276 @default.
- W2997646596 cites W1595205399 @default.
- W2997646596 cites W1595498733 @default.
- W2997646596 cites W2022485595 @default.
- W2997646596 cites W2025525377 @default.
- W2997646596 cites W2058142975 @default.
- W2997646596 cites W2100717205 @default.
- W2997646596 cites W2106334424 @default.
- W2997646596 cites W2112796928 @default.
- W2997646596 cites W2143381319 @default.
- W2997646596 cites W2143785942 @default.
- W2997646596 cites W2167757882 @default.
- W2997646596 cites W2186820913 @default.
- W2997646596 cites W2200124539 @default.
- W2997646596 cites W2221104225 @default.
- W2997646596 cites W2407793339 @default.
- W2997646596 cites W2467110937 @default.
- W2997646596 cites W2519112510 @default.
- W2997646596 cites W2531315337 @default.
- W2997646596 cites W2592232824 @default.
- W2997646596 cites W2612983688 @default.
- W2997646596 cites W2624871570 @default.
- W2997646596 cites W2742079690 @default.
- W2997646596 cites W2750384547 @default.
- W2997646596 cites W2791763440 @default.
- W2997646596 cites W2808938483 @default.
- W2997646596 cites W2809290718 @default.
- W2997646596 cites W2890538051 @default.
- W2997646596 cites W2892614179 @default.
- W2997646596 cites W2895387432 @default.
- W2997646596 cites W2913340405 @default.
- W2997646596 cites W2962743139 @default.
- W2997646596 cites W2963090765 @default.
- W2997646596 cites W2963493651 @default.
- W2997646596 cites W2963498646 @default.
- W2997646596 cites W2963677766 @default.
- W2997646596 cites W2963690600 @default.
- W2997646596 cites W2963703618 @default.
- W2997646596 cites W2963872552 @default.
- W2997646596 cites W2964128364 @default.
- W2997646596 cites W2964185501 @default.
- W2997646596 cites W2964259004 @default.
- W2997646596 cites W2964331719 @default.
- W2997646596 cites W3034672970 @default.
- W2997646596 doi "https://doi.org/10.48550/arxiv.1912.12854" @default.
- W2997646596 hasPublicationYear "2019" @default.
- W2997646596 type Work @default.
- W2997646596 sameAs 2997646596 @default.
- W2997646596 citedByCount "5" @default.
- W2997646596 countsByYear W29976465962021 @default.
- W2997646596 countsByYear W29976465962022 @default.
- W2997646596 countsByYear W29976465962023 @default.
- W2997646596 crossrefType "posted-content" @default.
- W2997646596 hasAuthorship W2997646596A5000546219 @default.
- W2997646596 hasAuthorship W2997646596A5008386708 @default.
- W2997646596 hasAuthorship W2997646596A5024948361 @default.
- W2997646596 hasAuthorship W2997646596A5031170152 @default.
- W2997646596 hasAuthorship W2997646596A5068670330 @default.
- W2997646596 hasBestOaLocation W29976465961 @default.
- W2997646596 hasConcept C11413529 @default.
- W2997646596 hasConcept C119857082 @default.
- W2997646596 hasConcept C126255220 @default.
- W2997646596 hasConcept C127413603 @default.
- W2997646596 hasConcept C137635306 @default.
- W2997646596 hasConcept C137836250 @default.
- W2997646596 hasConcept C154945302 @default.
- W2997646596 hasConcept C177264268 @default.
- W2997646596 hasConcept C199360897 @default.
- W2997646596 hasConcept C201995342 @default.
- W2997646596 hasConcept C2780451532 @default.
- W2997646596 hasConcept C2986314615 @default.
- W2997646596 hasConcept C33923547 @default.
- W2997646596 hasConcept C41008148 @default.
- W2997646596 hasConcept C68781425 @default.
- W2997646596 hasConceptScore W2997646596C11413529 @default.
- W2997646596 hasConceptScore W2997646596C119857082 @default.
- W2997646596 hasConceptScore W2997646596C126255220 @default.
- W2997646596 hasConceptScore W2997646596C127413603 @default.
- W2997646596 hasConceptScore W2997646596C137635306 @default.
- W2997646596 hasConceptScore W2997646596C137836250 @default.
- W2997646596 hasConceptScore W2997646596C154945302 @default.
- W2997646596 hasConceptScore W2997646596C177264268 @default.
- W2997646596 hasConceptScore W2997646596C199360897 @default.
- W2997646596 hasConceptScore W2997646596C201995342 @default.
- W2997646596 hasConceptScore W2997646596C2780451532 @default.
- W2997646596 hasConceptScore W2997646596C2986314615 @default.
- W2997646596 hasConceptScore W2997646596C33923547 @default.
- W2997646596 hasConceptScore W2997646596C41008148 @default.
- W2997646596 hasConceptScore W2997646596C68781425 @default.
- W2997646596 hasLocation W29976465961 @default.