Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
This work is significant for researchers and practitioners working with dynamic knowledge graphs, as it offers an incremental improvement in predicting missing temporal facts by exploiting historical repetition.
This paper addresses the incompleteness of temporal knowledge graphs by proposing CyGNet, a model that leverages historical patterns to predict missing temporal facts. CyGNet can predict future facts from the entire entity vocabulary and identify and predict repetitive facts by referencing past occurrences, showing effectiveness on five benchmark datasets.
Large knowledge graphs often grow to store temporal facts that model the dynamic relations or interactions of entities along the timeline. Since such temporal knowledge graphs often suffer from incompleteness, it is important to develop time-aware representation learning models that help to infer the missing temporal facts. While the temporal facts are typically evolving, it is observed that many facts often show a repeated pattern along the timeline, such as economic crises and diplomatic activities. This observation indicates that a model could potentially learn much from the known facts appeared in history. To this end, we propose a new representation learning model for temporal knowledge graphs, namely CyGNet, based on a novel timeaware copy-generation mechanism. CyGNet is not only able to predict future facts from the whole entity vocabulary, but also capable of identifying facts with repetition and accordingly predicting such future facts with reference to the known facts in the past. We evaluate the proposed method on the knowledge graph completion task using five benchmark datasets. Extensive experiments demonstrate the effectiveness of CyGNet for predicting future facts with repetition as well as de novo fact prediction.