TKGF-NTP: Temporal Knowledge Graph Forecasting via Neural Temporal Point Process

Knowledge graphs (KGs) with real-world facts are vital for various downstream applications. However, the incomplete nature of KGs has brought lots of problems to them, and probing missing facts via reasoning or forecasting has become a promising solution. Different from the traditional KG reasoning focusing on static facts, temporal knowledge graph (TKG) forecasting incorporating time information presents more potential in event prediction, as many facts are dynamic in real-world. Despite the significance of TKG forecasting, the following inevitable problems bring great challenges for it. (1) How to alleviate the problem of temporal fact redundancy in the TKG? (2) How to merge the useful fragmented temporal facts for the given query throughout the TKG? To overcome these problems effectively, we propose a novel model entitled TKGF-NTP, which consists of two components. (1) A structural encoder is developed to aggregate the most valuable structural information and filter out the redundant temporal facts from each TKG snapshot. (2) A temporal encoder is designed to capture the evolutions of entities, while the self-attention mechanism is employed to capture the most crucial temporal information throughout the TKG. The effectiveness of TKGF-NTP is evaluated on four public datasets via link prediction, and the results demonstrate its superiority over the state-of-the-art methods.