Efficient Learning-Based Graph Simulation for Temporal Graphs

Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on...

Full description

Saved in:
Bibliographic Details
Published in:Data engineering pp. 251 - 264
Main Authors: Xiang, Sheng, Xu, Chenhao, Cheng, Dawei, Wang, Xiaoyang, Zhang, Ying
Format: Conference Proceeding
Language:English
Published: IEEE 19.05.2025
Subjects:
Autoencoders
Biology
Generators
Graph Neural Network
Graph neural networks
Graph Simulation
Information technology
Learning systems
Memory management
Social sciences
Surges
Temporal Graphs
Training
ISSN:2375-026X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on static graphs, the temporal information of the graphs is ignored. In this paper, we focus on simulating temporal graphs, which aim to reproduce the structural and temporal properties of the observed real-life temporal graphs. In this paper, we first give an overview of the existing temporal graph generators, including recently emerged learning-based approaches. Most of these learning-based methods suffer from one of the limitations: low efficiency in training or slow generating, especially for temporal random walk-based methods. Therefore, we propose an efficient learning-based approach to generate graph snapshots, namely temporal graph autoencoder (TGAE). Specifically, we propose an attention-based graph encoder to encode temporal and structural characteristics on sampled ego-graphs. And we proposed an ego-graph decoder that can achieve a good trade-off between simulation quality and efficiency in temporal graph generation. Finally, the experimental evaluation is conducted among our proposed TGAE and representative temporal graph generators on real-life temporal graphs and synthesized graphs. It is reported that our proposed approach outperforms the state-of-the-art temporal graph generators by means of simulation quality and efficiency.
AbstractList Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on static graphs, the temporal information of the graphs is ignored. In this paper, we focus on simulating temporal graphs, which aim to reproduce the structural and temporal properties of the observed real-life temporal graphs. In this paper, we first give an overview of the existing temporal graph generators, including recently emerged learning-based approaches. Most of these learning-based methods suffer from one of the limitations: low efficiency in training or slow generating, especially for temporal random walk-based methods. Therefore, we propose an efficient learning-based approach to generate graph snapshots, namely temporal graph autoencoder (TGAE). Specifically, we propose an attention-based graph encoder to encode temporal and structural characteristics on sampled ego-graphs. And we proposed an ego-graph decoder that can achieve a good trade-off between simulation quality and efficiency in temporal graph generation. Finally, the experimental evaluation is conducted among our proposed TGAE and representative temporal graph generators on real-life temporal graphs and synthesized graphs. It is reported that our proposed approach outperforms the state-of-the-art temporal graph generators by means of simulation quality and efficiency.
Author Zhang, Ying
Cheng, Dawei
Xu, Chenhao
Wang, Xiaoyang
Xiang, Sheng
Author_xml – sequence: 1
  givenname: Sheng
  surname: Xiang
  fullname: Xiang, Sheng
  email: sheng.xiang@uts.edu.au
  organization: Australian Artificial Intelligence Institute, University of Technology Sydney,Sydney,Australia
– sequence: 2
  givenname: Chenhao
  surname: Xu
  fullname: Xu, Chenhao
  email: xuchenhao@stu.pku.edu.cn
  organization: School of Computer Science, Peking University,Beijing,China
– sequence: 3
  givenname: Dawei
  surname: Cheng
  fullname: Cheng, Dawei
  email: dcheng@tongji.edu.cn
  organization: School of Computer Science and Technology, Tongji University,Shanghai Artificial Intelligence Laboratory,Shanghai,China
– sequence: 4
  givenname: Xiaoyang
  surname: Wang
  fullname: Wang, Xiaoyang
  email: xiaoyang.wang1@unsw.edu.au
  organization: School of Computer Science and Engineering, University of New South Wales,Sydney,Australia
– sequence: 5
  givenname: Ying
  surname: Zhang
  fullname: Zhang, Ying
  email: ying.zhang@uts.edu.au
  organization: Australia Artificial Intelligence Institute, University of Technology Sydney,Sydney,Australia
BookMark eNotjL1OhEAURkejievKG2zBC4B3mB-YwkJxXTchsZDCbnMZ7ugYGAhg4dtLsp7mK86Xc8uuwhCIsR2HlHMw98fyea-VlEWaQaZSAMj0BYtMbgohuBIahLlkm0zkKlnVxw2L5vl7vYGRnCvYsIe9c956CktcEU7Bh8_kCWdq48OE41f87vufDhc_hNgNU1xTPw4Tdmc737Frh91M0f9uWf2yr8vXpHo7HMvHKvFGLInWKrcILUhREM_bBrEx1kFrWyUyoworDVnrCsV1AxYJjRNkWyPzBvOsEVu2O2c9EZ3Gyfc4_Z74igCuxR8QdUw2
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICDE65448.2025.00026
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Biology
Computer Science
EISBN 9798331536039
EISSN 2375-026X
EndPage 264
ExternalDocumentID 11113016
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation of China
  grantid: 62472317
  funderid: 10.13039/501100001809
– fundername: Fundamental Research Funds for the Central Universities
  grantid: 22YS1400600,24692118300
  funderid: 10.13039/501100012226
– fundername: ARC
  grantid: LP210301046,DP230101445,DP230101445,DP240101322
  funderid: 10.13039/100000163
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i93t-6657ca0d0438e17dbaab9cf0dcd532958c49eccf8516b0caea9f3ecd947ba72b3
IEDL.DBID RIE
IngestDate Wed Aug 27 07:41:07 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-6657ca0d0438e17dbaab9cf0dcd532958c49eccf8516b0caea9f3ecd947ba72b3
PageCount 14
ParticipantIDs ieee_primary_11113016
PublicationCentury 2000
PublicationDate 2025-May-19
PublicationDateYYYYMMDD 2025-05-19
PublicationDate_xml – month: 05
  year: 2025
  text: 2025-May-19
  day: 19
PublicationDecade 2020
PublicationTitle Data engineering
PublicationTitleAbbrev ICDE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000941150
Score 2.2987459
Snippet Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and...
SourceID ieee
SourceType Publisher
StartPage 251
SubjectTerms Autoencoders
Biology
Generators
Graph Neural Network
Graph neural networks
Graph Simulation
Information technology
Learning systems
Memory management
Social sciences
Surges
Temporal Graphs
Training
Title Efficient Learning-Based Graph Simulation for Temporal Graphs
URI https://ieeexplore.ieee.org/document/11113016
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEJ0I0cQTihi_04PXSre73W6vIqgXQiIHbqSfZhMFA4uJ_962u6AXD96a9tBk2slMZ_reA7i1VHKeZw5zIqx_oGiNlZMcJ8wWqZZK01RHsQk-HhezmZg0YPWIhbHWxs9n9i4MYy_fLPUmlMr6wb39hcxb0PIb1GCtXUHFv1NCdtPA4xIi-s-Dh2HOsviDi4bSSaRQ-CWiEmPIqPPP3Y-g94PGQ5NdnDmGPbvowkEtIvnVhc5WmAE1fnoCgZO4jEhH1PCnvuJ7H64Megz81OilfG9Uu5DPWdG0pqd6q1fXPZiOhtPBE250EnAp0gqH3omWxISenk24UVIqoR0x2rCUClboTPiDcj63yhXR0krhUquNyLiSnKr0FNqL5cKeAdJSEp-QcWoZz7w9FWd-PSWFoy4vDDuHXrDL_KNmwphvTXLxx_wlHAbTh257Iq6gXa029hr29WdVrlc38fy-Aa7Lm88
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED5BAcFUKEW88cAamthJHK-UllaUqhIZulV-BUWCFvWBxL_HdtzCwsBm2ZEi3dm6852_7wO41ZhTmsZFQEOmzQVFykAUnAZRojMiuZCYSCc2QYfDbDxmIw9Wd1gYrbV7fKbv7ND18tVMrmyprGWPt9mQ6TbsWOksD9falFTMTcXmNx4gF4Ws1W8_dFLzqX3DhW3xxJEo_JJRcVGkW__n_w-h-YPHQ6NNpDmCLT1twF4lI_nVgPpamgH5k3oMlpW4dFhH5BlUX4N7E7AUerQM1eilfPe6XchkrSivCKreqtVFE_JuJ2_3Aq-UEJSMLAPbPZE8VLarpyOqBOeCySJUUiUEsySTMTOuKkx2lYpQcs1ZQbRULKaCUyzICdSms6k-BSQ5D01KRrFOaGzsKWhi1kmYFbhIM5WcQdPaZfJRcWFM1iY5_2P-BvZ7-fNgMugPny7gwLrB9t4jdgm15Xylr2BXfi7Lxfza-fIb_myfGA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Data+engineering&rft.atitle=Efficient+Learning-Based+Graph+Simulation+for+Temporal+Graphs&rft.au=Xiang%2C+Sheng&rft.au=Xu%2C+Chenhao&rft.au=Cheng%2C+Dawei&rft.au=Wang%2C+Xiaoyang&rft.date=2025-05-19&rft.pub=IEEE&rft.eissn=2375-026X&rft.spage=251&rft.epage=264&rft_id=info:doi/10.1109%2FICDE65448.2025.00026&rft.externalDocID=11113016