Temporal knowledge graph (TKG) reasoning aims to predict the future missing facts based on historical information and has gained increasing research interest recently. Lots of works have been made to model the historical structural and temporal characteristics for the reasoning task. Most existing works model the graph structure mainly depending on entity representation. However, the magnitude of TKG entities in real-world scenarios is considerable, and an increasing number of new entities will arise as time goes on. Therefore, we propose a novel architecture modeling with relation feature of TKG, namely aDAptivE path-MemOry Network (DaeMon), which adaptively models the temporal path information between query subject and each object candidate across history time. It models the historical information without depending on entity representation. Specifically, DaeMon uses path memory to record the temporal path information derived from path aggregation unit across timeline considering the memory passing strategy between adjacent timestamps. Extensive experiments conducted on four real-world TKG datasets demonstrate that our proposed model obtains substantial performance improvement and outperforms the state-of-the-art up to 4.8% absolute in MRR.

本文提出了一种新的建模技术，即DAeMon(Based on Adaptive path-Memory Network)，该技术通过自适应地建模历史信息中关系特征，而不是仅仅依赖于实体表示；使用了路径记忆来记录时间线上的路径信息，并考虑邻近时间戳之间的记忆传递策略，实现了特定于时间的知识图谱(TKG)的推理，取得了实验数据集中相当大的性能改善，并在平均倒数排名(MRR)上跑赢了最新的竞争方法，达到了4.8% 的绝对性能提升。

适应性路径记忆网络用于时态知识图谱推理