Event Prediction using Case-Based Reasoning over Knowledge Graphs
This addresses the challenge of inductive link prediction for event entities in knowledge graphs, which is incremental as it adapts existing case-based reasoning to a specific domain.
The paper tackles the problem of predicting properties about new consequent events in knowledge graphs, where typical link prediction models fail due to inability to handle unseen entities and retraining needs. The result is that EvCBR, a case-based reasoning model, outperforms baselines on a novel dataset of newsworthy events from Wikidata.
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.