HALO: Half Life-Based Outdated Fact Filtering in Temporal Knowledge Graphs
This work addresses a specific issue in TKG reasoning by filtering outdated facts, which is an incremental improvement over existing methods that neglect this aspect.
The paper tackles the problem of outdated facts in temporal knowledge graphs (TKGs) by proposing HALO, a framework that filters such facts using half-life theory, resulting in improved reasoning performance and reduced computational costs, with experimental results showing it outperforms state-of-the-art methods on three public datasets.
Outdated facts in temporal knowledge graphs (TKGs) result from exceeding the expiration date of facts, which negatively impact reasoning performance on TKGs. However, existing reasoning methods primarily focus on positive importance of historical facts, neglecting adverse effects of outdated facts. Besides, training on these outdated facts yields extra computational cost. To address these challenges, we propose an outdated fact filtering framework named HALO, which quantifies the temporal validity of historical facts by exploring the half-life theory to filter outdated facts in TKGs. HALO consists of three modules: the temporal fact attention module, the dynamic relation-aware encoder module, and the outdated fact filtering module. Firstly, the temporal fact attention module captures the evolution of historical facts over time to identify relevant facts. Secondly, the dynamic relation-aware encoder module is designed for efficiently predicting the half life of each fact. Finally, we construct a time decay function based on the half-life theory to quantify the temporal validity of facts and filter outdated facts. Experimental results show that HALO outperforms the state-of-the-art TKG reasoning methods on three public datasets, demonstrating its effectiveness in detecting and filtering outdated facts (Codes are available at https://github.com/yushuowiki/K-Half/tree/main ).