본문

서브메뉴

Advancing Graph Neural Networks for Complex Data: A Perspective Beyond Homophily
Advancing Graph Neural Networks for Complex Data: A Perspective Beyond Homophily
Advancing Graph Neural Networks for Complex Data: A Perspective Beyond Homophily

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153018
ISBN  
9798384046165
DDC  
004
저자명  
Zhu, Jiong.
서명/저자  
Advancing Graph Neural Networks for Complex Data: A Perspective Beyond Homophily
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
257 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
주기사항  
Advisor: Koutra, Danai.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약Graph Neural Networks (GNNs) have demonstrated significant potential in extending the empirical success of deep learning from Euclidean spaces to non-Euclidean, graph-structured data. These models operate on versatile relational networks to extract meaningful representations, enabling a wide range of downstream applications such as friend recommendations, fraud detection, and bioinformatics. A key principle underlying many real-world networks-and often implicitly leveraged by GNN models-is homophily, whereby linked nodes often belong to the same class or have similar features ("birds of a feather flock together"). However, real-world settings where "opposites attract" also exist, resulting in networks characterized by heterophily, where linked nodes are likely from different classes or possess dissimilar features. How do GNNs perform in settings where the homophily is weak? Is the reduced accuracy of GNNs under heterophily related to their limitations in other performance aspects such as robustness, fairness, and scalability? This dissertation aims to push forward the state-of-the-art in GNNs by addressing these questions. In Part I, I focus on understanding and improving GNN accuracy beyond homophily. I first examine the limitations of existing GNN models under heterophily for semi-supervised node classification tasks, introducing key design strategies and new methods that significantly enhance learning from the graph structure on such datasets. Furthermore, I extend this analysis to link prediction tasks by formalizing the definitions of non-homophilic link prediction based on feature similarity, analyzing how different link prediction encoders and decoders adapt to varying levels of feature similarity, and introducing designs for improved performance. In Part II, I explore the implications of heterophily on other critical GNN research objectives beyond accuracy, including adversarial robustness, algorithmic fairness, and distributed scalability. My findings reveal that addressing heterophily not only enhances GNN accuracy but also improves their robustness and fairness, making them more suitable for deployment in complex real-world applications. Additionally, I show that heterophily is key to streamlining distributed training of GNNs on massive graphs, reducing communication overhead and improving efficiency and scalability. Overall, this dissertation advances the field of GNNs by moving beyond homophily, offering new insights and methodologies for handling heterophilous graph datasets, and demonstrating the broader benefits of these advancements in terms of robustness, fairness, and scalability.
일반주제명  
Computer science
일반주제명  
Computer engineering
일반주제명  
Information technology
키워드  
Graph Neural Networks
키워드  
Heterophily
키워드  
Machine learning
키워드  
Data mining
키워드  
Homophily
기타저자  
University of Michigan Computer Science & Engineering
기본자료저록  
Dissertations Abstracts International. 86-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164575
■00520250211153018
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384046165
■035    ▼a(MiAaPQ)AAI31631558
■035    ▼a(MiAaPQ)umichrackham005704
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aZhu,  Jiong.
■24510▼aAdvancing  Graph  Neural  Networks  for  Complex  Data:  A  Perspective  Beyond  Homophily
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a257  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Koutra,  Danai.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aGraph  Neural  Networks  (GNNs)  have  demonstrated  significant  potential  in  extending  the  empirical  success  of  deep  learning  from  Euclidean  spaces  to  non-Euclidean,  graph-structured  data.  These  models  operate  on  versatile  relational  networks  to  extract  meaningful  representations,  enabling  a  wide  range  of  downstream  applications  such  as  friend  recommendations,  fraud  detection,  and  bioinformatics.  A  key  principle  underlying  many  real-world  networks-and  often  implicitly  leveraged  by  GNN  models-is  homophily,  whereby  linked  nodes  often  belong  to  the  same  class  or  have  similar  features  ("birds  of  a  feather  flock  together").  However,  real-world  settings  where  "opposites  attract"  also  exist,  resulting  in  networks  characterized  by  heterophily,  where  linked  nodes  are  likely  from  different  classes  or  possess  dissimilar  features.  How  do  GNNs  perform  in  settings  where  the  homophily  is  weak?  Is  the  reduced  accuracy  of  GNNs  under  heterophily  related  to  their  limitations  in  other  performance  aspects  such  as  robustness,  fairness,  and  scalability?  This  dissertation  aims  to  push  forward  the  state-of-the-art  in  GNNs  by  addressing  these  questions.  In  Part  I,  I  focus  on  understanding  and  improving  GNN  accuracy  beyond  homophily.  I  first  examine  the  limitations  of  existing  GNN  models  under  heterophily  for  semi-supervised  node  classification  tasks,  introducing  key  design  strategies  and  new  methods  that  significantly  enhance  learning  from  the  graph  structure  on  such  datasets.  Furthermore,  I  extend  this  analysis  to  link  prediction  tasks  by  formalizing  the  definitions  of  non-homophilic  link  prediction  based  on  feature  similarity,  analyzing  how  different  link  prediction  encoders  and  decoders  adapt  to  varying  levels  of  feature  similarity,  and  introducing  designs  for  improved  performance.  In  Part  II,  I  explore  the  implications  of  heterophily  on  other  critical  GNN  research  objectives  beyond  accuracy,  including  adversarial  robustness,  algorithmic  fairness,  and  distributed  scalability.  My  findings  reveal  that  addressing  heterophily  not  only  enhances  GNN  accuracy  but  also  improves  their  robustness  and  fairness,  making  them  more  suitable  for  deployment  in  complex  real-world  applications.  Additionally,  I  show  that  heterophily  is  key  to  streamlining  distributed  training  of  GNNs  on  massive  graphs,  reducing  communication  overhead  and  improving  efficiency  and  scalability.  Overall,  this  dissertation  advances  the  field  of  GNNs  by  moving  beyond  homophily,  offering  new  insights  and  methodologies  for  handling  heterophilous  graph  datasets,  and  demonstrating  the  broader  benefits  of  these  advancements  in  terms  of  robustness,  fairness,  and  scalability.
■590    ▼aSchool  code:  0127.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■650  4▼aInformation  technology
■653    ▼aGraph  Neural  Networks
■653    ▼aHeterophily
■653    ▼aMachine  learning
■653    ▼aData  mining
■653    ▼aHomophily
■690    ▼a0984
■690    ▼a0800
■690    ▼a0489
■690    ▼a0464
■71020▼aUniversity  of  Michigan▼bComputer  Science  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164575▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF11606 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.