CountTRuCoLa: Rule Confidence Learning for Temporal Knowledge Graph Forecasting
This provides an interpretable solution for temporal knowledge graph forecasting, which is incremental as it builds on existing rule-based approaches.
The paper tackled temporal knowledge graph forecasting by introducing an explainable method based on temporal rules with a confidence function, achieving performance that matches or surpasses eight state-of-the-art models and two baselines across nine datasets.
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.