skip to main content
10.1145/3690407.3690587acmotherconferencesArticle/Chapter ViewAbstractPublication PagescaibdaConference Proceedingsconference-collections
research-article

Research on Temporal Graph for Link Prediction Method Based on Deep Learning

Published: 24 October 2024 Publication History

Abstract

In response to the drawbacks of inadequate structural feature mining in existing temporal graph link prediction methods, this paper proposes a method of structural feature extraction for temporal graph based on attenuated attention. The method effectively solves the problem that traditional methods assign the same weight to the knowledge graph relationship paths and ignore the rich information presented by adjacent nodes, which leads to incomplete mining of quaternion features and insufficient feature extraction. Meanwhile, this paper introduces an attention decay coefficient to differentiate the extraction of multi-hop neighbor node features according to the distance from the current entity, which makes the feature mining of the temporal graph structure more adequate. Secondly, this paper proposes a link prediction method of temporal graph based on the decreasing history information, which effectively solves the problem that traditional static knowledge graph link prediction methods lack the time dimension information and is not applicable to the link prediction of temporal graph. The traditional recursive mechanism of temporal graph is combined with weight decay to consider the decreasing effect of historical facts. Finally, the entity frequency-based temporal graph feature fusion method is used to fuse the decaying attention-based temporal graph structure feature extraction method and the historical decreasing information-based temporal graph link prediction method according to the entity frequency.

References

[1]
ZHANG Tiancheng, TIAN Xue, SUN Xianghui, et al. Overview on Knowledge Graph Embedding Technology Research [J]. Journal of Software, 2021, 34 (1): 277-311.
[2]
HUANG Liwei, LI Deyi, MA Yutao, et al. A Meta Path-Based Link Prediction Model for Heterogeneous Information Networks [J]. Journal of Computers, 2014, 37 (4): 848-858.
[3]
LIU Kangzheng, ZHAO Feng, Jin Hai. FS-Net: Frequency Statistical Network for Temporal Knowledge Graph Reasoning [J]. Journal of Software, 2023, 34 (10): 0-0.
[4]
Nickel M, Rosasco L, Poggio T. Holographic embeddings of knowledge graphs[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2016, 30 (1).
[5]
LIU H, WU Y, YANG Y. Analogical inference for multi-relational embeddings[C]//International conference on machine learning. PMLR, 2017: 2168-2178.
[6]
YANG B, Yih W, HE X, et al. Embedding entities and relations for learning and inference in knowledge bases[J]. arXiv preprint arXiv: 1412.6575, 2014.
[7]
Leblay J, Chekol M W. Deriving validity time in knowledge graph[C]//Companion proceedings of the the web conference 2018. 2018: 1771-1776.
[8]
Lacroix T, Obozinski G, Usunier N. Tensor Decompositions for temporal knowledge base completion[J]. 2020.
[9]
Trouillon T, Welbl J, Riedel S, et al. Complex Embeddings for Simple Link Prediction[J]. JMLR. org, 2016.
[10]
Dasgupta S S, Ray S N, Talukdar P. HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.
[11]
Goel R, Kazemi S M, Brubaker M, et al. Diachronic Embedding for Temporal Knowledge Graph Completion[C]// 2020: 3988-3995.
[12]
Pareja A, Domeniconi G, Chen J, et al. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs[J]. 2019.
[13]
SHANG C, TANG Y, HUANG J, et al. End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion[J]. arXiv, 2018.
[14]
Palm R B, Paquet U, Winther O. Recurrent Relational Networks[J]. 2017.
[15]
Cheung J, WU J, CAO M, et al. TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion, 2020.

Index Terms

  1. Research on Temporal Graph for Link Prediction Method Based on Deep Learning

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    CAIBDA '24: Proceedings of the 2024 4th International Conference on Artificial Intelligence, Big Data and Algorithms
    June 2024
    1206 pages
    ISBN:9798400710247
    DOI:10.1145/3690407
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 24 October 2024

    Check for updates

    Author Tags

    1. Deep Learning
    2. Knowledge Graph
    3. Link Prediction
    4. Temporal Graph

    Qualifiers

    • Research-article

    Conference

    CAIBDA 2024

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 28
      Total Downloads
    • Downloads (Last 12 months)28
    • Downloads (Last 6 weeks)6
    Reflects downloads up to 16 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    Full Text

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media