Abstract
Temporal Knowledge Graph (TKG) reasoning is based on historical information to predict the future. Therefore, parsing and mining historical information is key to predicting the future. Most existing methods fail to concurrently address and comprehend historical information from both global and local perspectives. Neglecting the global view might result in overlooking macroscopic trends and patterns, while ignoring the local view can lead to missing critical detailed information. Additionally, some methods do not focus on learning from high-frequency repeating events, which means they may not fully grasp frequently occurring historical events. To this end, we propose the \textbf{R}epetitive-\textbf{L}ocal-\textbf{G}lobal History \textbf{Net}work(RLGNet). We utilize a global history encoder to capture the overarching nature of historical information. Subsequently, the local history encoder provides information related to the query timestamp. Finally, we employ the repeating history encoder to identify and learn from frequently occurring historical events. In the evaluation on six benchmark datasets, our approach generally outperforms existing TKG reasoning models in multi-step and single-step reasoning tasks.
Abstract (translated)
temporal knowledge graph(TKG)推理是基于历史信息预测未来的。因此,解析和挖掘历史信息是预测未来的关键。大多数现有方法都没有同时从全局和局部角度解决和理解历史信息。忽视全局观点可能会导致忽视宏观趋势和模式,而忽略局部观点可能会导致遗漏关键的详细信息。此外,一些方法没有专注于从高频率重复事件中学习,这意味着它们可能没有完全理解经常发生的历史事件。为此,我们提出了重复-局部-全局历史网络(RLGNet)。我们利用全局历史编码器来捕捉历史信息的总体特征。接着,局部历史编码器提供与查询时间戳相关的信息。最后,我们使用重复历史编码器来识别并学习经常发生的历史事件。在六个基准数据集的评估中,我们的方法在多步和单步推理任务上通常比现有的TKG推理模型表现出色。
URL
https://arxiv.org/abs/2404.00586