DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Jeong, Wonyong | - |
dc.contributor.author | 정원용 | - |
dc.date.accessioned | 2024-07-26T19:30:25Z | - |
dc.date.available | 2024-07-26T19:30:25Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1046587&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320817 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iv, 88 p. :] | - |
dc.description.abstract | The conventional deep learning methods, which involve centralizing data for training, have given rise to concerns regarding privacy. As a response, Federated Learning has emerged as a viable alternative, wherein individual models are trained on local devices without directly sharing data, and the acquired knowledge is then integrated into a global model. However, existing Federated Learning techniques encounter certain limitations when confronted with the growing heterogeneity among participants. In this study, we identify six key challenges: (1) the lack or absence of labels, (2) disparities in domains and labels among participants, (3) challenges related to continual learning and forgetting, (4) issues pertaining to learning from relational data, (5) discrepancies in computational capabilities among participants, and (6) the retrieval of optimal neural network models. To tackle these challenges, we propose a Loosely-Constrained Federated Learning framework, which enables participants with diverse heterogeneity to share mutually beneficial knowledge for the purpose of learning. We demonstrate that our proposed methods surpass existing approaches in terms of performance and communication efficiency for each of the aforementioned problems. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 연합학습▼a개인습 연합학습▼a자동화 기계학습 | - |
dc.subject | Federated learning▼aPersonalized federated learning▼aAutoML | - |
dc.title | Loosely-constrained federated learning for heterogeneous local participants | - |
dc.title.alternative | 이종 로컬 참여자를 위한 소제약 연합학습 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Hwang, Sung Ju | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.