DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Moon, Jaekyun | - |
dc.contributor.advisor | 문재균 | - |
dc.contributor.author | Park, Jungwuk | - |
dc.date.accessioned | 2022-04-27T19:31:13Z | - |
dc.date.available | 2022-04-27T19:31:13Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948709&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295982 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iv, 29 p. :] | - |
dc.description.abstract | While federated learning allows efficient model training with local data at edge devices, two major issues that need to be resolved are: slow devices known as stragglers and malicious attacks launched by adversaries. While the presence of both stragglers and adversaries raises serious concerns for the deployment of practical federated learning systems, no known schemes or known combinations of schemes, to our best knowledge, effectively address these two issues at the same time. In this work, we propose Sself, a semi-synchronous entropy and loss based filtering/averaging, to tackle both stragglers and adversaries simultaneously. A theoretical convergence bound is established to provide insights on the convergence of Sself. Extensive experimental results show that Sself outperforms various combinations of existing methods aiming to handle stragglers/adversaries. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Federated learning▼astraggler▼aadversarial attack▼asemi-synchronous update▼arobust aggregation method | - |
dc.subject | 연합학습▼a스트래글러▼a악의적 공격▼a반 동기적 업데이트▼a강인한 집계 방식 | - |
dc.title | Robust federated learning against stragglers and adversaries | - |
dc.title.alternative | 반 동기식으로 수행되며 악의적 공격에 강인한 연합학습 알고리즘 개발 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 박정욱 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.