서브메뉴
검색
Towards Effective and Efficient Graph Neural Networks
Towards Effective and Efficient Graph Neural Networks
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151256
- ISBN
- 9798381972092
- DDC
- 004
- 저자명
- Wang, Yewen.
- 서명/저자
- Towards Effective and Efficient Graph Neural Networks
- 발행사항
- [Sl] : University of California, Los Angeles, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 164 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-09, Section: B.
- 주기사항
- Advisor: Sun, Yizhou.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- 초록/해제
- 요약Graph is a pervasive data type in the real world, as it serves as a succinct yet powerful abstraction for entities and their interconnections. Consequently, generating high-quality graph representations that encode the graph information is important, as these representations would be instrumental in graph-related tasks. In this context, Graph Neural Networks (GNNs) have emerged as a significant advancement and gained prominence for their ability to learn powerful graph representations which lead to state-of-the-art performance across a variety of graph-based applications.However, despite their remarkable capabilities, the design and training processes of GNNs are still fraught with challenges. Given this, my research goal is to identify and address these hurdles from both the effectiveness and efficiency perspectives, aiming to develop GNN models that are potent yet scalable, thereby enhancing GNN's power in producing superior graph representations in practice. This dissertation systematically investigates two fundamental questions: (1) What impedes the effectiveness of GNNs? (2) How to train GNNs efficiently? Despite providing a comprehensive discussion of each question, it presents practical solutions to mitigate each side and covers both homogeneous graphs and heterogeneous graphs.
- 일반주제명
- Computer science
- 키워드
- Effectiveness
- 키워드
- Efficiency
- 기타저자
- University of California, Los Angeles Computer Science 0201
- 기본자료저록
- Dissertations Abstracts International. 85-09B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161090
■00520250211151256
■006m o d
■007cr#unu||||||||
■020 ▼a9798381972092
■035 ▼a(MiAaPQ)AAI31141036
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aWang, Yewen.
■24510▼aTowards Effective and Efficient Graph Neural Networks
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a164 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-09, Section: B.
■500 ▼aAdvisor: Sun, Yizhou.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aGraph is a pervasive data type in the real world, as it serves as a succinct yet powerful abstraction for entities and their interconnections. Consequently, generating high-quality graph representations that encode the graph information is important, as these representations would be instrumental in graph-related tasks. In this context, Graph Neural Networks (GNNs) have emerged as a significant advancement and gained prominence for their ability to learn powerful graph representations which lead to state-of-the-art performance across a variety of graph-based applications.However, despite their remarkable capabilities, the design and training processes of GNNs are still fraught with challenges. Given this, my research goal is to identify and address these hurdles from both the effectiveness and efficiency perspectives, aiming to develop GNN models that are potent yet scalable, thereby enhancing GNN's power in producing superior graph representations in practice. This dissertation systematically investigates two fundamental questions: (1) What impedes the effectiveness of GNNs? (2) How to train GNNs efficiently? Despite providing a comprehensive discussion of each question, it presents practical solutions to mitigate each side and covers both homogeneous graphs and heterogeneous graphs.
■590 ▼aSchool code: 0031.
■650 4▼aComputer science
■653 ▼aEffectiveness
■653 ▼aEfficiency
■653 ▼aGraph Neural Networks
■653 ▼aHeterogeneous Graph Neural Networks
■690 ▼a0984
■71020▼aUniversity of California, Los Angeles▼bComputer Science 0201.
■7730 ▼tDissertations Abstracts International▼g85-09B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161090▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
