History repeats itself: A Baseline for Temporal Knowledge Graph Forecasting

International Joint Conference on Artificial Intelligence

We propose a temporal knowledge graph baseline based on the simple principle of recurrency. Surprisingly, a simple approach like this beats state of the art methods based on representation learning on 3 out of 5 commonly used datasets!

Federico Errica
Federico Errica
Research Scientist

My research interests include distributed robotics, mobile computing and programmable matter.