본문

서브메뉴

Network Alignment Using Topological and Node Embedding Features
Network Alignment Using Topological and Node Embedding Features
Network Alignment Using Topological and Node Embedding Features

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153108
ISBN  
9798346506775
DDC  
006
저자명  
Almulhim, Aljohara.
서명/저자  
Network Alignment Using Topological and Node Embedding Features
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
75 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: A.
주기사항  
Advisor: Hasan, Mohammad Al;Tuceryan, Mihran.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약In today's big data environment, development of robust knowledge discovery solutions depends on integration of data from various sources. For example, intelligence agencies fuse data from multiple sources to identify criminal activities; e-commerce platforms consolidate user activities on various platforms and devices to build better user profile; scientists connect data from various modality to develop new drugs, and treatments. In all such activities, entities from different data sources need to be aligned-first, to ensure accurate analysis and more importantly, to discover novel knowledge regarding these entities. If the data sources are networks, aligning entities from different sources leads to the task of network alignment, which is the focus of this thesis. The main objective of this task is to find an optimal oneto-one correspondence among nodes in two or more networks utilizing graph topology and nodes/edges attributes.In existing works, diverse computational schemes have been adopted for solving the network alignment task; these schemes include finding eigen-decomposition of similarity matrices, solving quadratic assignment problems via sub-gradient optimization, and designing iterative greedy matching techniques. Contemporary works approach this problem using a deep learning framework by learning node representations to identify matches. Node matching's key challenges include computational complexity and scalability. However, privacy concerns or unavailability often prevent the utilization of node attributes in real-world scenarios. In light of this, we aim to solve this problem by relying solely on the graph structure, without the need for prior knowledge, external attributes, or guidance from landmark nodes. Clearly, topology-based matching emerges as a hard problem when compared to other network matching tasks.In this thesis, I propose two original works to solve network topology-based alignment task. The first work, Graphlet-based Alignment (Graphlet-Align), employs a topological approach to network alignment. Graphlet-Align represents each node with a local graphlet count based signature and use that as feature for deriving node to node similarity across a pair of networks. By using these similarity values in a bipartite matching algorithm GraphletAlign obtains a preliminary alignment. It then uses high-order information extending to k-hop neighborhood of a node to further refine the alignment, achieving better accuracy. We validated Graphlet-Align's efficacy by applying it to various large real-world networks, achieving accuracy improvements ranging from 20% to 72% over state-of-the-art methods on both duplicated and noisy graphs.Expanding on this paradigm that focuses solely on topology for solving graph alignment, in my second work, I develop a self-supervised learning framework known as Self-Supervised Topological Alignment (SST-Align). SST-Align uses graphlet-based signature for creating self-supervised node alignment labels, and then use those labels to generate node embedding vectors of both the networks in a joint space from which node alignment task can be effectively and accurately solved. It starts with an optimization process that applies average pooling on top of the extracted graphlet signature to construct an initial node assignment. Next, a self-supervised Siamese network architecture utilizes both the initial node assignment and graph convolutional networks to generate node embeddings through a contrastive loss. By applying kd-tree similarity to the two networks' embeddings, we achieve the final node mapping. Extensive testing on real-world graph alignment datasets shows that our developed methodology has competitive results compared to seven existing competing models in terms of node mapping accuracy. Additionally, we establish the Ablation Study to evaluate the two-stage accuracy, excluding the learning representation part and comparing the mapping accuracy accordingly.This thesis enhances the theoretical understanding of topological features in the analysis of graph data for network alignment task, hence facilitating future advancements toward the field.
일반주제명  
Deep learning
일반주제명  
Graphs
일반주제명  
Computer vision
일반주제명  
Assignment problem
일반주제명  
Social network analysis
일반주제명  
Neural networks
일반주제명  
Eigenvalues
일반주제명  
Eigenvectors
일반주제명  
Computer science
일반주제명  
Web studies
일반주제명  
Mathematics
일반주제명  
Social structure
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-05A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164964
■00520250211153108
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346506775
■035    ▼a(MiAaPQ)AAI31682045
■035    ▼a(MiAaPQ)Purdue26357713
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a006
■1001  ▼aAlmulhim,  Aljohara.
■24510▼aNetwork  Alignment  Using  Topological  and  Node  Embedding  Features
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a75  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  A.
■500    ▼aAdvisor:  Hasan,  Mohammad  Al;Tuceryan,  Mihran.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼aIn  today's  big  data  environment,  development  of  robust  knowledge  discovery  solutions  depends  on  integration  of  data  from  various  sources.  For  example,  intelligence  agencies  fuse  data  from  multiple  sources  to  identify  criminal  activities;  e-commerce  platforms  consolidate  user  activities  on  various  platforms  and  devices  to  build  better  user  profile;  scientists  connect  data  from  various  modality  to  develop  new  drugs,  and  treatments.  In  all  such  activities,  entities  from  different  data  sources  need  to  be  aligned-first,  to  ensure  accurate  analysis  and  more  importantly,  to  discover  novel  knowledge  regarding  these  entities.  If  the  data  sources  are  networks,  aligning  entities  from  different  sources  leads  to  the  task  of  network  alignment,  which  is  the  focus  of  this  thesis.  The  main  objective  of  this  task  is  to  find  an  optimal  oneto-one  correspondence  among  nodes  in  two  or  more  networks  utilizing  graph  topology  and  nodes/edges  attributes.In  existing  works,  diverse  computational  schemes  have  been  adopted  for  solving  the  network  alignment  task;  these  schemes  include  finding  eigen-decomposition  of  similarity  matrices,  solving  quadratic  assignment  problems  via  sub-gradient  optimization,  and  designing  iterative  greedy  matching  techniques.  Contemporary  works  approach  this  problem  using  a  deep  learning  framework  by  learning  node  representations  to  identify  matches.  Node  matching's  key  challenges  include  computational  complexity  and  scalability.  However,  privacy  concerns  or  unavailability  often  prevent  the  utilization  of  node  attributes  in  real-world  scenarios.  In  light  of  this,  we  aim  to  solve  this  problem  by  relying  solely  on  the  graph  structure,  without  the  need  for  prior  knowledge,  external  attributes,  or  guidance  from  landmark  nodes.  Clearly,  topology-based  matching  emerges  as  a  hard  problem  when  compared  to  other  network  matching  tasks.In  this  thesis,  I  propose  two  original  works  to  solve  network  topology-based  alignment  task.  The  first  work,  Graphlet-based  Alignment  (Graphlet-Align),  employs  a  topological  approach  to  network  alignment.  Graphlet-Align  represents  each  node  with  a  local  graphlet  count  based  signature  and  use  that  as  feature  for  deriving  node  to  node  similarity  across  a  pair  of  networks.  By  using  these  similarity  values  in  a  bipartite  matching  algorithm  GraphletAlign  obtains  a  preliminary  alignment.  It  then  uses  high-order  information  extending  to  k-hop  neighborhood  of  a  node  to  further  refine  the  alignment,  achieving  better  accuracy.  We  validated  Graphlet-Align's  efficacy  by  applying  it  to  various  large  real-world  networks,  achieving  accuracy  improvements  ranging  from  20%  to  72%  over  state-of-the-art  methods  on  both  duplicated  and  noisy  graphs.Expanding  on  this  paradigm  that  focuses  solely  on  topology  for  solving  graph  alignment,  in  my  second  work,  I  develop  a  self-supervised  learning  framework  known  as  Self-Supervised  Topological  Alignment  (SST-Align).  SST-Align  uses  graphlet-based  signature  for  creating  self-supervised  node  alignment  labels,  and  then  use  those  labels  to  generate  node  embedding  vectors  of  both  the  networks  in  a  joint  space  from  which  node  alignment  task  can  be  effectively  and  accurately  solved.  It  starts  with  an  optimization  process  that  applies  average  pooling  on  top  of  the  extracted  graphlet  signature  to  construct  an  initial  node  assignment.  Next,  a  self-supervised  Siamese  network  architecture  utilizes  both  the  initial  node  assignment  and  graph  convolutional  networks  to  generate  node  embeddings  through  a  contrastive  loss.  By  applying  kd-tree  similarity  to  the  two  networks'  embeddings,  we  achieve  the  final  node  mapping.  Extensive  testing  on  real-world  graph  alignment  datasets  shows  that  our  developed  methodology  has  competitive  results  compared  to  seven  existing  competing  models  in  terms  of  node  mapping  accuracy.  Additionally,  we  establish  the  Ablation  Study  to  evaluate  the  two-stage  accuracy,  excluding  the  learning  representation  part  and  comparing  the  mapping  accuracy  accordingly.This  thesis  enhances  the  theoretical  understanding  of  topological  features  in  the  analysis  of  graph  data  for  network  alignment  task,  hence  facilitating  future  advancements  toward  the  field.
■590    ▼aSchool  code:  0183.
■650  4▼aDeep  learning
■650  4▼aGraphs
■650  4▼aComputer  vision
■650  4▼aAssignment  problem
■650  4▼aSocial  network  analysis
■650  4▼aNeural  networks
■650  4▼aEigenvalues
■650  4▼aEigenvectors
■650  4▼aComputer  science
■650  4▼aWeb  studies
■650  4▼aMathematics
■650  4▼aSocial  structure
■690    ▼a0800
■690    ▼a0984
■690    ▼a0646
■690    ▼a0405
■690    ▼a0796
■690    ▼a0700
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-05A.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164964▼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
    TF14428 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.