HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph

He, Yongquan; Zhang, Peng; Liu, Luchen; Liang, Qi; Zhang, Wenyuan; Zhang, Chuang

doi:10.24963/ijcai.2021/264

HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph

Yongquan He, Peng Zhang, Luchen Liu, Qi Liang, Wenyuan Zhang, Chuang Zhang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 1915-1921.

https://doi.org/10.24963/ijcai.2021/264

Keywords

Knowledge Representation and Reasoning: Qualitative, Geometric, Spatial, Temporal Reasoning
Natural Language Processing: Embeddings

Abstract

In recent years, temporal knowledge graph (TKG) reasoning has received significant attention. Most existing methods assume that all timestamps and corresponding graphs are available during training, which makes it difficult to predict future events. To address this issue, recent works learn to infer future events based on historical information. However, these methods do not comprehensively consider the latent patterns behind temporal changes, to pass historical information selectively, update representations appropriately and predict events accurately. In this paper, we propose the Historical Information Passing (HIP) network to predict future events. HIP network passes information from temporal, structural and repetitive perspectives, which are used to model the temporal evolution of events, the interactions of events at the same time step, and the known events respectively. In particular, our method considers the updating of relation representations and adopts three scoring functions corresponding to the above dimensions. Experimental results on five benchmark datasets show the superiority of HIP network, and the significant improvements on Hits@1 prove that our method can more accurately predict what is going to happen.

Yongquan He, Peng Zhang, Luchen Liu, Qi Liang, Wenyuan Zhang, and Chuang Zhang. 2021. HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 1915–1921. https://doi.org/10.24963/ijcai.2021/264

@inproceedings{ijcai2021p264,
  title     = {HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph},
  author    = {He, Yongquan and Zhang, Peng and Liu, Luchen and Liang, Qi and Zhang, Wenyuan and Zhang, Chuang},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {1915--1921},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/264},
  url       = {https://doi.org/10.24963/ijcai.2021/264},
}

TY  - CPAPER
TI  - HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
AU  - He, Yongquan
AU  - Zhang, Peng
AU  - Liu, Luchen
AU  - Liang, Qi
AU  - Zhang, Wenyuan
AU  - Zhang, Chuang
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 1915
EP  - 1921
DO  - 10.24963/ijcai.2021/264
UR  - https://doi.org/10.24963/ijcai.2021/264
ER  -