HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs

Tingxuan Chen, Jun Long, Liu Yang, Zidong Wang, Yongheng Wang, Xiongnan Jin


Abstract
Temporal knowledge graphs (TKGs) serve as powerful tools for storing and modeling dynamic facts, holding immense potential in anticipating future facts. Since future facts are inherently unknowable, effectively modeling the intricate temporal structure of historical facts becomes paramount for accurate prediction. However, current models often rely heavily on fact recurrence or periodicity, leading to information loss due to prolonged evolutionary processes. Notably, the occurrence of one fact always influences the likelihood of another. To this end, we propose HTCCN, a novel Hawkes process-based temporal causal convolutional network designed for temporal reasoning under extrapolation settings. HTCCN employs a temporal causal convolutional network to model the historical interdependence of facts and leverages Hawkes to model link formation processes inductively in TKGs. Importantly, HTCCN introduces dual-level dynamics to comprehensively capture the temporal evolution of facts. Rigorous experimentation on four real-world datasets underscores the superior performance of HTCCN.
Anthology ID:
2024.naacl-long.225
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4056–4066
Language:
URL:
https://aclanthology.org/2024.naacl-long.225
DOI:
10.18653/v1/2024.naacl-long.225
Bibkey:
Cite (ACL):
Tingxuan Chen, Jun Long, Liu Yang, Zidong Wang, Yongheng Wang, and Xiongnan Jin. 2024. HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4056–4066, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs (Chen et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.225.pdf