Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks

TL;DR

This paper introduces CyGNet, a time-aware copy-generation model for temporal knowledge graphs that leverages historical fact patterns to improve future fact prediction, addressing incompleteness in dynamic, time-evolving data.

Contribution

It proposes a novel copy-generation mechanism within a neural network to model repeated temporal patterns and enhance knowledge graph completion.

Findings

CyGNet outperforms existing models on five benchmark datasets.

Effective in predicting both repeated and new facts.

Demonstrates significant improvement in temporal knowledge graph completion.

Abstract

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.