Towards predicting future time intervals on Temporal Knowledge Graphs

Roxana Pop, Egor Kostylev

Keywords: Temporal Knowledge Graphs, Time Prediction, Time Intervals, Forecasting

TL;DR: Short paper describing a system for predicting 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.

Format: Short paper, up to 4 pages.

Submission Number: 43