Federated transfer learning under heterogeneous data
Saved in:
| Title: | Federated transfer learning under heterogeneous data |
|---|---|
| Authors: | Wu, Xueyang |
| Contributors: | Yang, Qiang, Chen, Lei |
| Publication Year: | 2022 |
| Collection: | The Hong Kong University of Science and Technology: HKUST Institutional Repository |
| Subject Terms: | Transfer learning (Machine learning), Data privacy, Heterogeneous distributed computing systems |
| Description: | Recent advancements in artificial intelligence (AI) applications rely on massive amounts of training data. In practice, these valuable data are independently distributed among multiple data owners (e.g., companies and individuals), whose quantities are typically modest, and the data are usually heterogeneous. Collecting data from individual users or acquiring data from data owners is a conventionally popular and straightforward solution to this issue. However, such solutions have become obsolete due to the rising trend of data privacy and data security concerns. Currently, AI systems face the problem of utilizing fragmented and diverse data that are independently distributed across several data owners. Federated learning (FL), a novel privacy-preserving collaborative machine learning paradigm, is proposed to address the privately isolated small data learning problem. Its main idea is to compose a federation of data owners in which all participants virtually assemble their data without sacrificing data security and privacy. There are several challenges for federated learning, including communication efficiency, data security and privacy protection, and statistical learning. Among these challenges, the statistical learning challenge caused by heterogeneous data significantly affects the performance of FL systems and thus prohibits FL’s applications in practice. In recent years, academics have developed a machine learning paradigm known as transfer learning, which utilizes heterogeneous data to solve the statistical learning issue in the target domain with limited or no data. Naturally, it motivates us to incorporate the spirit of transfer learning into federated learning to overcome the difficulty of statistical learning in practical FL. In this thesis, we focus on federated transfer learning, a class of federated learning methods that employ the transfer learning methodology to tackle the statistical learning difficulty posed by heterogeneous data. Compared to other federated learning approaches, which presume ... |
| Document Type: | thesis |
| Language: | English |
| Availability: | http://repository.hkust.edu.hk/ir/Record/1783.1-137280 https://repository.hkust.edu.hk/ir/bitstream/1783.1-137280/1/991013160256703412.pdf |
| Accession Number: | edsbas.9E3A3D5C |
| Database: | BASE |
Nájsť tento článok vo Web of Science | FullText | Text: Availability: 0 CustomLinks: – Url: http://repository.hkust.edu.hk/ir/Record/1783.1-137280# Name: EDS - BASE (s4221598) Category: fullText Text: View record from BASE – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Wu%20X Name: ISI Category: fullText Text: Nájsť tento článok vo Web of Science Icon: https://imagesrvr.epnet.com/ls/20docs.gif MouseOverText: Nájsť tento článok vo Web of Science |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.9E3A3D5C RelevancyScore: 772 AccessLevel: 3 PubType: Dissertation/ Thesis PubTypeId: dissertation PreciseRelevancyScore: 772.276306152344 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Federated transfer learning under heterogeneous data – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wu%2C+Xueyang%22">Wu, Xueyang</searchLink> – Name: Author Label: Contributors Group: Au Data: Yang, Qiang<br />Chen, Lei – Name: DatePubCY Label: Publication Year Group: Date Data: 2022 – Name: Subset Label: Collection Group: HoldingsInfo Data: The Hong Kong University of Science and Technology: HKUST Institutional Repository – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Transfer+learning+%28Machine+learning%29%22">Transfer learning (Machine learning)</searchLink><br /><searchLink fieldCode="DE" term="%22Data+privacy%22">Data privacy</searchLink><br /><searchLink fieldCode="DE" term="%22Heterogeneous+distributed+computing+systems%22">Heterogeneous distributed computing systems</searchLink> – Name: Abstract Label: Description Group: Ab Data: Recent advancements in artificial intelligence (AI) applications rely on massive amounts of training data. In practice, these valuable data are independently distributed among multiple data owners (e.g., companies and individuals), whose quantities are typically modest, and the data are usually heterogeneous. Collecting data from individual users or acquiring data from data owners is a conventionally popular and straightforward solution to this issue. However, such solutions have become obsolete due to the rising trend of data privacy and data security concerns. Currently, AI systems face the problem of utilizing fragmented and diverse data that are independently distributed across several data owners. Federated learning (FL), a novel privacy-preserving collaborative machine learning paradigm, is proposed to address the privately isolated small data learning problem. Its main idea is to compose a federation of data owners in which all participants virtually assemble their data without sacrificing data security and privacy. There are several challenges for federated learning, including communication efficiency, data security and privacy protection, and statistical learning. Among these challenges, the statistical learning challenge caused by heterogeneous data significantly affects the performance of FL systems and thus prohibits FL’s applications in practice. In recent years, academics have developed a machine learning paradigm known as transfer learning, which utilizes heterogeneous data to solve the statistical learning issue in the target domain with limited or no data. Naturally, it motivates us to incorporate the spirit of transfer learning into federated learning to overcome the difficulty of statistical learning in practical FL. In this thesis, we focus on federated transfer learning, a class of federated learning methods that employ the transfer learning methodology to tackle the statistical learning difficulty posed by heterogeneous data. Compared to other federated learning approaches, which presume ... – Name: TypeDocument Label: Document Type Group: TypDoc Data: thesis – Name: Language Label: Language Group: Lang Data: English – Name: URL Label: Availability Group: URL Data: http://repository.hkust.edu.hk/ir/Record/1783.1-137280<br />https://repository.hkust.edu.hk/ir/bitstream/1783.1-137280/1/991013160256703412.pdf – Name: AN Label: Accession Number Group: ID Data: edsbas.9E3A3D5C |
| PLink | https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.9E3A3D5C |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: English Subjects: – SubjectFull: Transfer learning (Machine learning) Type: general – SubjectFull: Data privacy Type: general – SubjectFull: Heterogeneous distributed computing systems Type: general Titles: – TitleFull: Federated transfer learning under heterogeneous data Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wu, Xueyang – PersonEntity: Name: NameFull: Yang, Qiang – PersonEntity: Name: NameFull: Chen, Lei IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2022 Identifiers: – Type: issn-locals Value: edsbas |
| ResultId | 1 |