RETIA: Relation-entity twin-interact aggregation for temporal knowledge graph extrapolation

Kangzheng LIU, Feng ZHAO, Guandong XU, Xianzhi WANG, Hai JIN

Research output: Chapter in Book/Report/Conference proceedingChapters

2 Citations (Scopus)

Abstract

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands"problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://github.com/CGCL-codes/RETIA. Copyright © 2023 IEEE.

Original languageEnglish
Title of host publicationProceedings of 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023
Place of PublicationUSA
PublisherIEEE
Pages1761-1774
ISBN (Electronic)9798350322279
DOIs
Publication statusPublished - 2023

Citation

Liu, K., Zhao, F., Xu, G., Wang, X., & Jin, H. (2023). RETIA: Relation-entity twin-interact aggregation for temporal knowledge graph extrapolation. In Proceedings of 2023 IEEE 39th International Conference on Data Engineering, ICDE 2023 (pp. 1761-1774). IEEE. https://doi.org/10.1109/ICDE55515.2023.00138

Keywords

  • Temporal knowledge graph extrapolation
  • Twin-interact aggregation
  • Graph convolutional network

Fingerprint

Dive into the research topics of 'RETIA: Relation-entity twin-interact aggregation for temporal knowledge graph extrapolation'. Together they form a unique fingerprint.