Efficient and Effective Edge-wise Graph Representation Learning

Hewen Wang, Renchi Yang, Keke Huang, Xiaokui Xiao

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

1 Citation (Scopus)

Abstract

Graph representation learning (GRL) is a powerful tool for graph analysis, which has gained massive attention from both academia and industry due to its superior performance in various real-world applications. However, the majority of existing works for GRL are dedicated to node-based tasks and thus focus on producing node representations. Despite such methods can be used to derive edge representations by regarding edges as nodes, they suffer from sub-par result utility in practical edge-wise applications, such as financial fraud detection and review spam combating, due to neglecting the unique properties of edges and their inherent drawbacks. Moreover, to our knowledge, there is a paucity of research devoted to edge representation learning. These methods either require high computational costs in sampling random walks or yield severely compromised representation quality because of falling short of capturing high-order information between edges. To address these challenges, we present TER and AER, which generate high-quality edge representation vectors based on the graph structure surrounding edges and edge attributes, respectively. In particular, TER can accurately encode high-order proximities of edges into low-dimensional vectors in a practically efficient and theoretically sound way, while AER augments edge attributes through a carefully-designed feature aggregation scheme. Our extensive experimental study demonstrates that the combined edge representations of TER and AER can achieve significantly superior performance in terms of edge classification on 8 real-life datasets, while being up to one order of magnitude faster than 16 baselines on large graphs.
Original languageEnglish
Title of host publicationKDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
EditorsAmbuj Singh, Yizhou Sun
PublisherAssociation for Computing Machinery (ACM)
Pages2326–2336
Number of pages11
ISBN (Print)9798400701030
DOIs
Publication statusPublished - Aug 2023
Event29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States
Duration: 6 Aug 202310 Aug 2023
https://kdd.org/kdd2023/
https://dl.acm.org/doi/proceedings/10.1145/3580305

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Country/TerritoryUnited States
CityLong Beach
Period6/08/2310/08/23
Internet address

Scopus Subject Areas

  • Software
  • Information Systems

User-Defined Keywords

  • attributed graph
  • edge classification
  • graph representation learning

Fingerprint

Dive into the research topics of 'Efficient and Effective Edge-wise Graph Representation Learning'. Together they form a unique fingerprint.

Cite this