Query-specific context-enhanced representation learning for temporal knowledge graph reasoning

Gao, Yu, Zeng, Qingtian, Ni, Weijian, Cheng, Cheng, Duan, Hua, Zou, Minghao and Wang, Ziyang 2026. Query-specific context-enhanced representation learning for temporal knowledge graph reasoning. Presented at: International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 3-8 May 2026. Proceedings of 2026 International Conference on Acoustics, Speech, and Signal Processing. IEEE, pp. 1371-1375. 10.1109/icassp55912.2026.11460415

Full text not available from this repository.

Abstract

Temporal Knowledge Graph Reasoning (TKGR) aims to leverage historical information to predict future facts. However, most existing methods learn entity embeddings shared across all queries at the same timestamp, without considering query-specific context. To tackle these problems, we propose Query-Specific Context-Enhanced Representation Learning (QSCEL) model for TKGR. Specifically, we construct an extended graph based on the query set to provide a structural basis for learning query-specific context. On this graph, we design a query-aware dual-attention graph neural network to learn both shared and query-specific contexts. Moreover, we design a global repeated history encoder that encodes fact frequency and temporal decay to better exploit historical information. Extensive experiments on four public datasets demonstrate the effectiveness of QSCEL. Our implementation is available at https://github.com/yugao9892/QSCEL.

Item Type:	Conference or Workshop Item - published (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	9798331567026
ISSN:	1520-6149
Last Modified:	07 May 2026 09:19
URI:	https://orca.cardiff.ac.uk/id/eprint/186842

Actions (repository staff only)

Edit Item