CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
By: Julia Gastinger, Christian Meilicke, Heiner Stuckenschmidt
Potential Business Impact:
Predicts future facts with easy-to-understand rules.
We address the task of temporal knowledge graph (TKG) forecasting by introducing a fully explainable method based on temporal rules. Motivated by recent work proposing a strong baseline using recurrent facts, our approach learns four simple types of rules with a confidence function that considers both recency and frequency. Evaluated on nine datasets, our method matches or surpasses the performance of eight state-of-the-art models and two baselines, while providing fully interpretable predictions.
Similar Papers
Temporal Knowledge Graph Hyperedge Forecasting: Exploring Entity-to-Category Link Prediction
Machine Learning (CS)
Explains future events using smart rules.
DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
Machine Learning (CS)
Predicts future events and fills in missing history.
Integrate Temporal Graph Learning into LLM-based Temporal Knowledge Graph Model
Information Retrieval
Predicts future events by understanding time and connections.