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
  • [31] Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
    Lv, Xin
    Gu, Yuxian
    Han, Xu
    Hou, Lei
    Li, Juanzi
    Liu, Zhiyuan
    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, : 3376 - 3381
  • [32] Few-Shot Multihop Question Answering over Knowledge Base
    Fan, Meihao
    Zhang, Lei
    Xiao, Siyao
    Liang, Yuru
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
  • [33] Learning Implicit Temporal Alignment for Few-shot Video Classification
    Zhang, Songyang
    Zhou, Jiale
    He, Xuming
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 1309 - 1315
  • [34] Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
    Lu, Bin
    Gan, Xiaoying
    Zhang, Weinan
    Yao, Huaxiu
    Fu, Luoyi
    Wang, Xinbing
    PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 1162 - 1172
  • [35] Multi-hop interpretable meta learning for few-shot temporal knowledge graph completion
    Bai, Luyi
    Han, Shuo
    Zhu, Lin
    NEURAL NETWORKS, 2025, 183
  • [36] Defensive Few-Shot Learning
    Li, Wenbin
    Wang, Lei
    Zhang, Xingxing
    Qi, Lei
    Huo, Jing
    Gao, Yang
    Luo, Jiebo
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (05) : 5649 - 5667
  • [37] Federated Few-shot Learning
    Wang, Song
    Fu, Xingbo
    Ding, Kaize
    Chen, Chen
    Chen, Huiyuan
    Li, Jundong
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 2374 - 2385
  • [38] CLG: Contrastive Label Generation with Knowledge for Few-Shot Learning
    Ma, Han
    Fan, Baoyu
    Ng, Benjamin K.
    Lam, Chan-Tong
    MATHEMATICS, 2024, 12 (03)
  • [39] Learning self-target knowledge for few-shot segmentation
    Chen, Yadang
    Chen, Sihan
    Yang, Zhi-Xin
    Wu, Enhua
    PATTERN RECOGNITION, 2024, 149
  • [40] Knowledge transduction for cross-domain few-shot learning
    Li, Pengfang
    Liu, Fang
    Jiao, Licheng
    Li, Shuo
    Li, Lingling
    Liu, Xu
    Huang, Xinyan
    PATTERN RECOGNITION, 2023, 141