Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs

被引:0
|
作者
Wang, Ruijie [1 ]
Li, Zheng [2 ]
Sun, Dachun [1 ]
Liu, Shengzhong [1 ]
Li, Jinning [1 ]
Yin, Bing [2 ]
Abdelzaher, Tarek [1 ]
机构
[1] Univ Illinois, Champaign, IL 61820 USA
[2] Amazon Com Inc, Santa Clara, CA USA
关键词
NETWORK;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we investigate a realistic but underexplored problem, called few-shot temporal knowledge graph reasoning, that aims to predict future facts for newly emerging entities based on extremely limited observations in evolving graphs. It offers practical value in applications that need to derive instant new knowledge about new entities in temporal knowledge graphs (TKGs) with minimal supervision. The challenges mainly come from the few-shot and time shift properties of new entities. First, the limited observations associated with them are insufficient for training a model from scratch. Second, the potentially dynamic distributions from the initially observable facts to the future facts ask for explicitly modeling the evolving characteristics of new entities. We correspondingly propose a novel Meta Temporal Knowledge Graph Reasoning (MetaTKGR) framework. Unlike prior work that relies on rigid neighborhood aggregation schemes to enhance low-data entity representation, MetaTKGR dynamically adjusts the strategies of sampling and aggregating neighbors from recent facts for new entities, through temporally supervised signals on future facts as instant feedback. Besides, such a meta temporal reasoning procedure goes beyond existing meta-learning paradigms on static knowledge graphs that fail to handle temporal adaptation with large entity variance. We further provide a theoretical analysis and propose a temporal adaptation regularizer to stabilize the meta temporal reasoning over time. Empirically, extensive experiments on three real-world TKGs demonstrate the superiority of MetaTKGR over state-of-the-art baselines by a large margin.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Adapting Distilled Knowledge for Few-shot Relation Reasoning over Knowledge Graphs
    Zhang, Yiming
    Qian, Yiyue
    Ye, Yanfang
    Zhang, Chuxu
    PROCEEDINGS OF THE 2022 SIAM INTERNATIONAL CONFERENCE ON DATA MINING, SDM, 2022, : 666 - 674
  • [2] Few-shot multi-hop reasoning via reinforcement learning and path search strategy over temporal knowledge graphs
    Bai, Luyi
    Zhang, Han
    An, Xuanxuan
    Zhu, Lin
    INFORMATION PROCESSING & MANAGEMENT, 2025, 62 (03)
  • [3] Few-shot link prediction with meta-learning for temporal knowledge graphs
    Zhu, Lin
    Xing, Yizong
    Bai, Luyi
    Chen, Xiwen
    JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING, 2023, 10 (02) : 711 - 721
  • [4] MetaHKG: Meta Hyperbolic Learning for Few-shot Temporal Reasoning
    Wang, Ruijie
    Zhang, Yutong
    Li, Jinyang
    Liu, Shengzhong
    Sun, Dachun
    Wang, Tianchen
    Wang, Tianshi
    Chen, Yizhuo
    Kara, Denizhan
    Abdelzaher, Tarek
    PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 59 - 69
  • [5] BayesKGR: Bayesian Few-Shot Learning for Knowledge Graph Reasoning
    Zhao, Feng
    Yan, Cheng
    Jin, Hai
    He, Lifang
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (06)
  • [6] Zero-Shot and Few-Shot Learning With Knowledge Graphs: A Comprehensive Survey
    Chen, Jiaoyan
    Geng, Yuxia
    Chen, Zhuo
    Pan, Jeff Z. Z.
    He, Yuan
    Zhang, Wen
    Horrocks, Ian
    Chen, Huajun
    PROCEEDINGS OF THE IEEE, 2023, 111 (06) : 653 - 685
  • [7] Knowledge Graph Reasoning for Few-Shot Problems
    Zhang, Xiaoli
    Guo, Jinhui
    Liang, Kun
    Xu, Gefei
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT IV, ICIC 2024, 2024, 14878 : 187 - 196
  • [8] Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs
    Ma, Ruixin
    Li, Zeyang
    Ma, Yunlong
    Wu, Hao
    Yu, Mengfei
    Zhao, Liang
    APPLIED SCIENCES-BASEL, 2022, 12 (09):
  • [9] Hybrid attention mechanism for few-shot relational learning of knowledge graphs
    Ma, Ruixin
    Li, Zeyang
    Guo, Fangqing
    Zhao, Liang
    IET COMPUTER VISION, 2021, 15 (08) : 561 - 572
  • [10] Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
    Chen, Mingyang
    Zhang, Wen
    Zhang, Wei
    Chen, Qiang
    Chen, Huajun
    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, : 4217 - 4226