Modeling Paths and History for Temporal Knowledge Graph Reasoning

Knowledge Graph (KG) reasoning is a crucial task that discovers potential and unknown knowledge based on the existing knowledge. Temporal Knowledge Graph (TKG) reasoning is more challenging than KG reasoning because the additional temporal information needs to be handled. Previous TKG reasoning methods restrict the search space to avoid huge computational consumption, resulting in a decrease in accuracy. In order to improve the accuracy and efficiency of TKG reasoning, a model CMPH (Combination Model of Paths and History) is proposed, which consists of a path memory network and a history memory network. The former finds the paths in advance by a TKG path search algorithm and learns to memorize the recurrent pattern for reasoning, which prevents path search at inference stage. The latter adopts efficient encoder-decoder architecture to learn the features of historical events in TKG, which can avoid tackling a large number of structural dependencies and increase the reasoning accuracy. To take the advantages of these two types of memory networks, a gate component is designed to integrate them for better performance. Extensive experiments on four real-world datasets demonstrate that the proposed model obtains substantial performance and efficiency improvement for the TKG reasoning tasks. Especially, it achieves up to 8.6% and 11.8% improvements in MRR and hit@1 respectively, and up to 21 times speedup at inference stage comparing to the state-of-the-art baseline.