DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 최윤재 | - |
dc.contributor.author | Yang, Seong-Jun | - |
dc.contributor.author | 양성준 | - |
dc.date.accessioned | 2024-07-22T19:30:07Z | - |
dc.date.available | 2024-07-22T19:30:07Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1044768&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320300 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2022.8,[iv, 22 p. :] | - |
dc.description.abstract | Federated learning (FL) is an active area of research. One of the most suitable areas for adopting FLis the medical domain, where patient privacy must be respected. Previous research, however, does notfully consider who will most likely use FL in the medical domain. It is not the hospitals who are eagerto adopt FL, but the service providers such as IT companies who want to develop artificial intelligencemodels with real patient records. Moreover, service providers would prefer to focus on maximizing theperformance of the models at the lowest cost possible. In this work, we propose empirical benchmarks ofFL methods considering both performance and monetary cost with three real-world datasets: electronichealth records, skin cancer images, and electrocardiogram datasets. We also propose Federated learningwith Proximal regularization eXcept local Normalization (FedPxN), which, using a simple combinationof FedProx and FedBN, outperforms all other FL algorithms while consuming only slightly more powerthan the most power efficient method. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 연합학습▼a의료도메인▼a데이터 이질성▼a비용▼a벤치마크 | - |
dc.subject | Federated learning▼aMedical domain▼aData heterogeneity▼aMonetary cost▼aBenchmark | - |
dc.title | (A) experimental survey of federated learning on the medical domain | - |
dc.title.alternative | 의료 분야에서 연합학습에 대한 실험적 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Choi, Edward | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.