Learning to Forget for Meta-Learning via Task-and-Layer-Wise Attenuation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Baik, Sungyong | - |
dc.contributor.author | Oh, Junghoon | - |
dc.contributor.author | Hong, Seokil | - |
dc.contributor.author | Lee, Kyoung Mu | - |
dc.date.accessioned | 2023-07-24T09:17:28Z | - |
dc.date.available | 2023-07-24T09:17:28Z | - |
dc.date.created | 2023-07-21 | - |
dc.date.issued | 2022-11 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/187270 | - |
dc.description.abstract | Few-shot learning is an emerging yet challenging problem in which the goal is to achieve generalization from only few examples. Meta-learning tackles few-shot learning via the learning of prior knowledge shared across tasks and using it to learn new tasks. One of the most representative meta-learning algorithms is the model-agnostic meta-learning (MAML), which formulates prior knowledge as a common initialization, a shared starting point from where a learner can quickly adapt to unseen tasks. However, forcibly sharing an initialization can lead to conflicts among tasks and the compromised (undesired by tasks) location on optimization landscape, thereby hindering task adaptation. Furthermore, the degree of conflict is observed to vary not only among the tasks but also among the layers of a neural network. Thus, we propose task-and-layer-wise attenuation on the compromised initialization to reduce its adverse influence on task adaptation. As attenuation dynamically controls (or selectively forgets) the influence of the compromised prior knowledge for a given task and each layer, we name our method Learn to Forget (L2F). Experimental results demonstrate that the proposed method greatly improves the performance of the state-of-the-art MAML-based frameworks across diverse domains: few-shot classification, cross-domain few-shot classification, regression, reinforcement learning, and visual tracking. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Learning to Forget for Meta-Learning via Task-and-Layer-Wise Attenuation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Baik, Sungyong | - |
dc.identifier.doi | 10.1109/TPAMI.2021.3102098 | - |
dc.identifier.scopusid | 2-s2.0-85112632974 | - |
dc.identifier.wosid | 000864325900034 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.44, no.11, pp.7718 - 7730 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.title | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.citation.volume | 44 | - |
dc.citation.number | 11 | - |
dc.citation.startPage | 7718 | - |
dc.citation.endPage | 7730 | - |
dc.type.rims | ART | - |
dc.type.docType | 정기학술지(Article(Perspective Article포함)) | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Adaptation models | - |
dc.subject.keywordPlus | Attenuation | - |
dc.subject.keywordPlus | Few-shot learning | - |
dc.subject.keywordPlus | Metalearning | - |
dc.subject.keywordPlus | Model-agnostic meta-learning | - |
dc.subject.keywordPlus | Neural-networks | - |
dc.subject.keywordPlus | Optimisations | - |
dc.subject.keywordPlus | Reinforcement learnings | - |
dc.subject.keywordPlus | Task analysis | - |
dc.subject.keywordPlus | Visual Tracking | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Optimization | - |
dc.subject.keywordAuthor | Adaptation models | - |
dc.subject.keywordAuthor | Attenuation | - |
dc.subject.keywordAuthor | Knowledge engineering | - |
dc.subject.keywordAuthor | Visualization | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Meta-learning | - |
dc.subject.keywordAuthor | few-shot learning | - |
dc.subject.keywordAuthor | MAML | - |
dc.subject.keywordAuthor | reinforcement learning | - |
dc.subject.keywordAuthor | visual tracking | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9507366 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.