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

author:

Wang, Jingbin (Wang, Jingbin.) [1] (Scholars:汪璟玢) | Lin, Xinyu (Lin, Xinyu.) [2] | Huang, Hao (Huang, Hao.) [3] | Ke, Xifan (Ke, Xifan.) [4] | Wu, Renfei (Wu, Renfei.) [5] | You, Changkai (You, Changkai.) [6] | Guo, Kun (Guo, Kun.) [7] (Scholars:郭昆)

Indexed by:

EI Scopus SCIE

Abstract:

Knowledge graph completion (KGC) has been widely explored, but the task of temporal knowledge graph completion (TKGC) for predicting future events is far from perfection. Some embedding-based approaches have achieved significant results on the TKGC task by modeling the structural information of each temporal snapshot and the evolution between temporal snapshots. However, due to the uneven distribution of data in knowledge graphs (KGs), models that only utilize local structure and time series information suffer from information sparsity, resulting in some entities failing to obtain a better embedding representation due to less available information. Moreover, existing methods usually do not distinguish between the time span and frequency of historical information, which reduces the performance of link prediction. For this reason, we propose the G lobal and L ocal Information-A ware Net work (GL-ANet) to capture both global and local information. In particular, to model global information, we capture global structural information of entities across time using a global neighborhood aggregator to enrich the representation of entities; global historical information is obtained based on the frequency and time span of historical facts, focusing on recent and frequent events rather than all historical events to suggest the performance of link prediction; to model local information, we propose a two-layer attention network to capture local structural information at each timestamp, using a gating mechanism and GRU to capture local evolution information. Extensive experiments demonstrate the effectiveness of our model, achieving significant improvements and outperforming state-of-the-art models on five benchmark datasets.

Keyword:

Global information Link prediction Local information Neighborhood aggregator Temporal knowledge graph

Community:

  • [ 1 ] [Wang, Jingbin]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 2 ] [Lin, Xinyu]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 3 ] [Huang, Hao]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 4 ] [Ke, Xifan]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 5 ] [Wu, Renfei]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 6 ] [You, Changkai]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China
  • [ 7 ] [Guo, Kun]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China

Reprint 's Address:

  • [Guo, Kun]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Fujian, Peoples R China;;

Show more details

Related Keywords:

Related Article:

Source :

APPLIED INTELLIGENCE

ISSN: 0924-669X

Year: 2023

Issue: 16

Volume: 53

Page: 19285-19301

3 . 4

JCR@2023

3 . 4 0 0

JCR@2023

ESI Discipline: ENGINEERING;

ESI HC Threshold:35

JCR Journal Grade:2

CAS Journal Grade:3

Cited Count:

WoS CC Cited Count: 3

SCOPUS Cited Count: 11

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 7

Online/Total:370/11071828
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1