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
  • [21] One-shot relational learning for extrapolation reasoning on temporal knowledge graphs
    Ruixin Ma
    Biao Mei
    Yunlong Ma
    Hongyan Zhang
    Meihong Liu
    Liang Zhao
    Data Mining and Knowledge Discovery, 2023, 37 : 1591 - 1608
  • [22] Few-Shot Few-Shot Learning and the role of Spatial Attention
    Lifchitz, Yann
    Avrithis, Yannis
    Picard, Sylvaine
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 2693 - 2700
  • [23] Prototype Completion with Primitive Knowledge for Few-Shot Learning
    Zhang, Baoquan
    Li, Xutao
    Ye, Yunming
    Huang, Zhichao
    Zhang, Lisai
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3753 - 3761
  • [24] Graph Few-Shot Learning via Knowledge Transfer
    Yao, Huaxiu
    Zhang, Chuxu
    Wei, Ying
    Jiang, Meng
    Wang, Suhang
    Huang, Junzhou
    Chawla, Nitesh, V
    Li, Zhenhui
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 6656 - 6663
  • [25] Hierarchical Knowledge Propagation and Distillation for Few-Shot Learning
    Zhou, Chunpeng
    Wang, Haishuai
    Zhou, Sheng
    Yu, Zhi
    Bandara, Danushka
    Bu, Jiajun
    NEURAL NETWORKS, 2023, 167 : 615 - 625
  • [26] Reallocating and Evolving General Knowledge for Few-Shot Learning
    Su, Yuling
    Liu, Xueliang
    Huang, Zhen
    He, Jun
    Hong, Richang
    Wang, Meng
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (12) : 13518 - 13529
  • [27] Symmetric Hallucination With Knowledge Transfer for Few-Shot Learning
    Wang, Shuo
    Zhang, Xinyu
    Wang, Meng
    He, Xiangnan
    IEEE TRANSACTIONS ON MULTIMEDIA, 2025, 27 : 1797 - 1807
  • [28] Multi-Hop Knowledge Graph Reasoning in Few-Shot Scenarios
    Zheng, Shangfei
    Chen, Wei
    Wang, Weiqing
    Zhao, Pengpeng
    Yin, Hongzhi
    Zhao, Lei
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (04) : 1713 - 1727
  • [29] Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language
    Ellis, Kevin
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [30] Knowledge Distillation Meets Few-Shot Learning: An Approach for Few-Shot Intent Classification Within and Across Domains
    Sauer, Anna
    Asaadi, Shima
    Kuech, Fabian
    PROCEEDINGS OF THE 4TH WORKSHOP ON NLP FOR CONVERSATIONAL AI, 2022, : 108 - 119