Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs

Zhen Han, Zifeng Ding, Yunpu Ma, Yujia Gu, Volker Tresp


Abstract
There has been an increasing interest in inferring future links on temporal knowledge graphs (KG). While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces. To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks. The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings. In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i.e., edge formation and dissolution. We perform extensive experiments on five benchmark datasets for temporal KG reasoning, showing our model’s superior performance on the future link forecasting task.
Anthology ID:
2021.emnlp-main.658
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8352–8364
Language:
URL:
https://aclanthology.org/2021.emnlp-main.658
DOI:
10.18653/v1/2021.emnlp-main.658
Bibkey:
Cite (ACL):
Zhen Han, Zifeng Ding, Yunpu Ma, Yujia Gu, and Volker Tresp. 2021. Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8352–8364, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs (Han et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.658.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.658.mp4
Data
ICEWS