DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Moon, Il-Chul | - |
dc.contributor.advisor | 문일철 | - |
dc.contributor.author | Shin, Yongjin | - |
dc.date.accessioned | 2022-04-21T19:31:13Z | - |
dc.date.available | 2022-04-21T19:31:13Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963730&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295311 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 산업및시스템공학과, 2021.8,[iii, 23 p. :] | - |
dc.description.abstract | Federated Learning is a distributed learning methodology for training a server model across devices that keep their data locally. Recently, Federated Learning has established itself as one of the research fields to address social issues as to privacy infringement. However, a distributed data environment do not follow the identical independent distribution, making it harder for existing methodologies of machine learning to be applied immediately. This data heterogeneity leads to over-fitting on local data in federated learning, which undermines the performance improvement of the server model. In this work, we present Localized Binary Cross-Entropy (LBCE) as a loss function to prevent over-fitting to local data in distributed environments. When a local machine learns a model using a conventional cross-entropy function, it uses error signals for a data class that does not belong to local data. Thus, to limit over-fitting, the LBCE loss function maintains the independence of each class by using a sigmoid function instead of a softmax activation function while regulating signals for data classes that do not belong to local data. LBCE outperformed conventional softmax cross-entropy in various situations of distributed data that did not follow the identical independent distribution. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Federated Learning▼aDistributed Learning▼aInternet of Things▼aData bias▼aCross-Entropy | - |
dc.subject | 연합 학습▼a분산 학습▼a사물 인터넷▼a편향 데이터▼a교차엔트로피 | - |
dc.title | Localized binary cross-entropy for federated learning | - |
dc.title.alternative | 연합 학습을 위한 지역적 교차 엔트로피 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :산업및시스템공학과, | - |
dc.contributor.alternativeauthor | 신용진 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.