Towards Predicting Future Time Intervals on Temporal Knowledge Graphs

Abstract

Temporal Knowledge Graphs (TKGs), a temporal extension of Knowledge Graphs where facts are contextualized by time information, have received increasing attention in the temporal graph learning community. In this short paper we focus on TKGs where the temporal contexts are time intervals, and address the time prediction problem in the forecasting setting. We propose both a system architecture for addressing the task and a benchmarking methodology.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Pop and Kostylev. "Towards Predicting Future Time Intervals on Temporal Knowledge Graphs." NeurIPS 2023 Workshops: TGL, 2023.

Markdown

[Pop and Kostylev. "Towards Predicting Future Time Intervals on Temporal Knowledge Graphs." NeurIPS 2023 Workshops: TGL, 2023.](https://mlanthology.org/neuripsw/2023/pop2023neuripsw-predicting/)

BibTeX

@inproceedings{pop2023neuripsw-predicting,
  title     = {{Towards Predicting Future Time Intervals on Temporal Knowledge Graphs}},
  author    = {Pop, Roxana and Kostylev, Egor},
  booktitle = {NeurIPS 2023 Workshops: TGL},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/pop2023neuripsw-predicting/}
}