서브메뉴
검색
Efficient Federated Graph Learning: Formulation, Algorithms and Applications.
Efficient Federated Graph Learning: Formulation, Algorithms and Applications.
상세정보
- 자료유형
- 학위논문
- Control Number
- 0017161449
- International Standard Book Number
- 9798383729649
- Dewey Decimal Classification Number
- 621.3
- Main Entry-Personal Name
- Yao, Yuhang.
- Publication, Distribution, etc. (Imprint
- [S.l.] : Carnegie Mellon University., 2024
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- Physical Description
- 173 p.
- General Note
- Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
- General Note
- Advisor: Joe-Wong, Carlee.
- Dissertation Note
- Thesis (Ph.D.)--Carnegie Mellon University, 2024.
- Summary, Etc.
- 요약Graph neural networks aim to learn representations of graph-structured data that capture features associated with graph nodes as well as edges between the nodes. The Graph data, however, can be too large to be trained on a single server or naturally exist on multiple local clients. Strict data protection regulations such as the General Data Protection Regulation (GDPR) in Europe and Payment Aggregators and Payment Gateways (PAPG) in India also require that private data only be stored in local clients. Users may also not want to share their personal data with the server. Federated learning shows promise for preserving user privacy while training accurate models training models on data stored at multiple clients. Federated graph learning is then becoming an emerging topic with practical challenges. However, compared with federated learning with local data heterogeneity, there is no clear identification of key challenges in federated graph learning. Derived from real-world applications, we point out three unique challenges for federated graph learning: cross-client edges, cross-device heterogeneity with limited local data and temporal heterogeneity across clients. We then respectively introduce FedGCN, FedRule, and FedLink to overcome the challenges. We finally provide the vision for the future direction of such a topic.
- Subject Added Entry-Topical Term
- Computer engineering.
- Subject Added Entry-Topical Term
- Statistics.
- Subject Added Entry-Topical Term
- Information technology.
- Index Term-Uncontrolled
- Federated graph learning
- Index Term-Uncontrolled
- Graph neural networks
- Index Term-Uncontrolled
- Private data
- Index Term-Uncontrolled
- Graph nodes
- Added Entry-Corporate Name
- Carnegie Mellon University Electrical and Computer Engineering
- Host Item Entry
- Dissertations Abstracts International. 86-02B.
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:658293
MARC
008250224s2024 us ||||||||||||||c||eng d■001000017161449
■00520250211151358
■006m o d
■007cr#unu||||||||
■020 ▼a9798383729649
■035 ▼a(MiAaPQ)AAI31243944
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a621.3
■1001 ▼aYao, Yuhang.▼0(orcid)0000-0002-7045-0002
■24510▼aEfficient Federated Graph Learning: Formulation, Algorithms and Applications.
■260 ▼a[S.l.]▼bCarnegie Mellon University. ▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a173 p.
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-02, Section: B.
■500 ▼aAdvisor: Joe-Wong, Carlee.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2024.
■520 ▼aGraph neural networks aim to learn representations of graph-structured data that capture features associated with graph nodes as well as edges between the nodes. The Graph data, however, can be too large to be trained on a single server or naturally exist on multiple local clients. Strict data protection regulations such as the General Data Protection Regulation (GDPR) in Europe and Payment Aggregators and Payment Gateways (PAPG) in India also require that private data only be stored in local clients. Users may also not want to share their personal data with the server. Federated learning shows promise for preserving user privacy while training accurate models training models on data stored at multiple clients. Federated graph learning is then becoming an emerging topic with practical challenges. However, compared with federated learning with local data heterogeneity, there is no clear identification of key challenges in federated graph learning. Derived from real-world applications, we point out three unique challenges for federated graph learning: cross-client edges, cross-device heterogeneity with limited local data and temporal heterogeneity across clients. We then respectively introduce FedGCN, FedRule, and FedLink to overcome the challenges. We finally provide the vision for the future direction of such a topic.
■590 ▼aSchool code: 0041.
■650 4▼aComputer engineering.
■650 4▼aStatistics.
■650 4▼aInformation technology.
■653 ▼aFederated graph learning
■653 ▼aGraph neural networks
■653 ▼aPrivate data
■653 ▼aGraph nodes
■690 ▼a0464
■690 ▼a0489
■690 ▼a0800
■690 ▼a0463
■71020▼aCarnegie Mellon University▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g86-02B.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161449▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
