Event Prediction using Case-Based Reasoning over Knowledge Graphs

TL;DR

This paper introduces EvCBR, a case-based reasoning approach for event prediction over knowledge graphs that effectively predicts new events without retraining, outperforming existing link prediction models.

Contribution

The paper presents EvCBR, a novel, training-free, case-based reasoning model for inductive event prediction over knowledge graphs, addressing limitations of traditional link prediction methods.

Findings

EvCBR outperforms baseline models on a new dataset of causal events.

The method effectively predicts properties of unseen events.

EvCBR requires no retraining as knowledge graphs evolve.

Abstract

Applying link prediction (LP) methods over knowledge graphs (KG) for tasks such as causal event prediction presents an exciting opportunity. However, typical LP models are ill-suited for this task as they are incapable of performing inductive link prediction for new, unseen event entities and they require retraining as knowledge is added or changed in the underlying KG. We introduce a case-based reasoning model, EvCBR, to predict properties about new consequent events based on similar cause-effect events present in the KG. EvCBR uses statistical measures to identify similar events and performs path-based predictions, requiring no training step. To generalize our methods beyond the domain of event prediction, we frame our task as a 2-hop LP task, where the first hop is a causal relation connecting a cause event to a new effect event and the second hop is a property about the new event which we wish to predict. The effectiveness of our method is demonstrated using a novel dataset of newsworthy events with causal relations curated from Wikidata, where EvCBR outperforms baselines including translational-distance-based, GNN-based, and rule-based LP models.