Resource-Efficient Multi-Task Deep Learning Using a Multi-Path Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, S. | - |
dc.contributor.author | Lee, J. | - |
dc.contributor.author | Kim, Eunwoo | - |
dc.date.accessioned | 2023-03-08T09:31:06Z | - |
dc.date.available | 2023-03-08T09:31:06Z | - |
dc.date.issued | 2022 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/61899 | - |
dc.description.abstract | Multi-task learning (MTL) improves learning efficiency compared to the single-task counterpart in that it performs multiple tasks at the same time. Due to the nature, it can achieve generalized performance as well as alleviate overfitting. However, it does not efficiently perform resource-aware inference from a single trained architecture. To address the issue, we aim to build a learning framework that minimizes the cost to infer tasks under different memory budgets. To this end, we propose a multi-path network with a self-auxiliary learning strategy. The multi-path structure contains task-specific paths in a backbone network, where a lower-level path predicts earlier with a smaller number of parameters. To alleviate the performance degradation from earlier predictions, a self-auxiliary learning strategy is presented. The self-auxiliary tasks convey task-specific knowledge to the main tasks to compensate for the performance leak. We evaluate the proposed method on an extensive set of multi-task learning scenarios, including multiple tasks learning, hierarchical learning, and curriculum learning. The proposed method outperforms existing multi-task learning competitors for most scenarios about by a margin of 1% ~ 2% accuracy on average while consuming 30% ~ 60% smaller computational cost. Author | - |
dc.format.extent | 11 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Resource-Efficient Multi-Task Deep Learning Using a Multi-Path Network | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3161622 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.10, pp 32889 - 32899 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000776163300001 | - |
dc.identifier.scopusid | 2-s2.0-85127058448 | - |
dc.citation.endPage | 32899 | - |
dc.citation.startPage | 32889 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 10 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Computer architecture | - |
dc.subject.keywordAuthor | Costs | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Interference | - |
dc.subject.keywordAuthor | Knowledge engineering | - |
dc.subject.keywordAuthor | multi-path network | - |
dc.subject.keywordAuthor | Multi-task learning | - |
dc.subject.keywordAuthor | Multitasking | - |
dc.subject.keywordAuthor | resource-efficient learning | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.