RE-SEGNN: recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

被引:0
|
作者
Cai, Wenyu [1 ]
Li, Mengfan [1 ]
Shi, Xuanhua [1 ]
Fan, Yuanxin [1 ]
Zhu, Quntao [1 ]
Jin, Hai [1 ]
机构
[1] Huazhong Univ Sci & Technol, Natl Engn Res Ctr Big Data Technol & Syst, Serv Comp Technol & Syst Lab, Sch Comp Sci & Technol,Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China
基金
国家重点研发计划;
关键词
knowledge graph reasoning; temporal knowledge graph; Hawkes process; semantic evidence;
D O I
10.1007/s11432-023-4073-y
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Temporal knowledge graph (TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be challenging. To address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network (RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting
    Wenyu CAI
    Mengfan LI
    Xuanhua SHI
    Yuanxin FAN
    Quntao ZHU
    Hai JIN
    Science China(Information Sciences), 2025, 68 (02) : 103 - 119
  • [2] Evidence-aware Fake News Detection with Graph Neural Networks
    Xu, Weizhi
    Wu, Junfei
    Liu, Qiang
    Wu, Shu
    Wang, Liang
    PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, : 2501 - 2510
  • [3] Decoupled semantic graph neural network for knowledge graph embedding
    Li, Zhifei
    Huang, Wei
    Gong, Xuchao
    Luo, Xiangyu
    Xiao, Kui
    Deng, Honglian
    Zhang, Miao
    Zhang, Yan
    NEUROCOMPUTING, 2025, 611
  • [4] Context-Aware Knowledge Graph Framework for Traffic Speed Forecasting Using Graph Neural Network
    Zhang, Yatao
    Wang, Yi
    Gao, Song
    Raubal, Martin
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2025, 26 (03) : 3885 - 3902
  • [5] Temporal-aware structure-semantic-coupled graph network for traffic forecasting
    Chen, Mao
    Han, Liangzhe
    Xu, Yi
    Zhu, Tongyu
    Wang, Jibin
    Sun, Leilei
    INFORMATION FUSION, 2024, 107
  • [6] Adversarial Contrastive Learning for Evidence-Aware Fake News Detection With Graph Neural Networks
    Wu, Junfei
    Xu, Weizhi
    Liu, Qiang
    Wu, Shu
    Wang, Liang
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (11) : 5591 - 5604
  • [7] Spatial and Temporal Aware Graph Convolutional Network for Flood Forecasting
    Feng, Jun
    Wang, Zhongyi
    Wu, Yirui
    Xi, Yuqi
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [8] DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
    Lan, Shiyong
    Ma, Yitong
    Huang, Weikang
    Wang, Wenwu
    Yang, Hongyu
    Li, Piaoyang
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [9] Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
    Fancellu, Federico
    Gilroy, Sorcha
    Lopez, Adam
    Lapata, Mirella
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2769 - 2778
  • [10] Semantic- and relation-based graph neural network for knowledge graph completion
    Li, Xinlu
    Tian, Yujie
    Ji, Shengwei
    APPLIED INTELLIGENCE, 2024, 54 (08) : 6085 - 6107