MSEN: A Multi-Scale Evolutionary Network for Modeling the Evolution of Temporal Knowledge Graphs

Yong Yu, Shudong Chen (), Rong Du, Da Tong, Hao Xu and Shuai Chen
Additional contact information
Yong Yu: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China
Shudong Chen: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China
Rong Du: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China
Da Tong: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China
Hao Xu: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China
Shuai Chen: Institute of Microelectronics of the Chinese Academy of Sciences, Beijing 100191, China

Future Internet, 2023, vol. 15, issue 10, 1-15

Abstract: Temporal knowledge graphs play an increasingly prominent role in scenarios such as social networks, finance, and smart cities. As such, research on temporal knowledge graphs continues to deepen. In particular, research on temporal knowledge graph reasoning holds great significance, as it can provide abundant knowledge for downstream tasks such as question answering and recommendation systems. Current reasoning research focuses primarily on interpolation and extrapolation. Extrapolation research aims to predict the likelihood of events occurring in future timestamps. Historical events are crucial for predicting future events. However, existing models struggle to fully capture the evolutionary characteristics of historical knowledge graphs. This paper proposes a multi-scale evolutionary network (MSEN) model that leverages Hierarchical Transfer aware Graph Neural Network (HT-GNN) in a local memory encoder to aggregate rich structural semantics from each timestamp’s knowledge graph. It also utilizes Time Related Graph Neural Network (TR-GNN) in a global memory encoder to model temporal-semantic dependencies of entities across the global knowledge graph, mining global evolutionary patterns. The model integrates information from both encoders to generate entity embeddings for predicting future events. The proposed MSEN model demonstrates strong performance compared to several baselines on typical benchmark datasets. Results show MSEN achieves the highest prediction accuracy.

Keywords: knowledge graph; temporal knowledge graph; knowledge graph reasoning; evolution of temporal knowledge graphs (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/15/10/327/pdf (application/pdf)
https://www.mdpi.com/1999-5903/15/10/327/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:15:y:2023:i:10:p:327-:d:1251852

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().