• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Li, Mengran (Li, Mengran.) | Zhang, Yong (Zhang, Yong.) (Scholars:张勇) | Li, Xiaoyong (Li, Xiaoyong.) | Zhang, Yuchen (Zhang, Yuchen.) | Yin, Baocai (Yin, Baocai.)

Indexed by:

EI Scopus SCIE

Abstract:

Graph neural networks (GNNs) have beenwidely used for graph structure learning and achieved excellent performance in tasks such as node classification and link prediction. Real-world graph networks imply complex and various semantic information and are often referred to as heterogeneous information networks (HINs). Previous GNNs have laboriously modeled heterogeneous graph networks with pairwise relations, in which the semantic information representation for learning is incomplete and severely hinders node embedded learning. Therefore, the conventional graph structure cannot satisfy the demand for information discovery in HINs. In this article, we propose an end-to-end hypergraph transformer neural network (HGTN) that exploits the communication abilities between different types of nodes and hyperedges to learn higher-order relations and discover semantic information. Specifically, attention mechanisms weigh the importance of semantic information hidden in original HINs to generate useful meta-paths. Meanwhile, our method develops a multi-scale attention module to aggregate node embeddings in higher-order neighborhoods. We evaluate the proposed model with node classification tasks on six datasets: DBLP, ACM, IBDM, Reuters, STUD-BJUT, and Citeseer. Experiments on a large number of benchmarks show the advantages of HGTN.

Keyword:

node classification attention Hypergraph meta-paths transformer

Author Community:

  • [ 1 ] [Li, Mengran]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China
  • [ 2 ] [Zhang, Yong]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China
  • [ 3 ] [Li, Xiaoyong]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China
  • [ 4 ] [Zhang, Yuchen]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China
  • [ 5 ] [Yin, Baocai]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China

Reprint Author's Address:

  • 张勇

    [Zhang, Yong]Beijing Univ Technol, Fac Informat Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China

Show more details

Related Keywords:

Source :

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA

ISSN: 1556-4681

Year: 2023

Issue: 5

Volume: 17

3 . 6 0 0

JCR@2022

ESI Discipline: COMPUTER SCIENCE;

ESI HC Threshold:19

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:622/5311755
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.