EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs

TL;DR

EvoKG is a novel framework for reasoning over temporal knowledge graphs that jointly models event timing and network evolution, significantly improving accuracy and efficiency in predicting future facts.

Contribution

It introduces a unified approach that simultaneously models event times and network structure changes in TKGs, addressing limitations of prior static or partial methods.

Findings

EvoKG achieves up to 77% more accurate time prediction.

EvoKG outperforms existing methods in link prediction accuracy.

The framework demonstrates improved efficiency in reasoning tasks.

Abstract

How can we perform knowledge reasoning over temporal knowledge graphs (TKGs)? TKGs represent facts about entities and their relations, where each fact is associated with a timestamp. Reasoning over TKGs, i.e., inferring new facts from time-evolving KGs, is crucial for many applications to provide intelligent services. However, despite the prevalence of real-world data that can be represented as TKGs, most methods focus on reasoning over static knowledge graphs, or cannot predict future events. In this paper, we present a problem formulation that unifies the two major problems that need to be addressed for an effective reasoning over TKGs, namely, modeling the event time and the evolving network structure. Our proposed method EvoKG jointly models both tasks in an effective framework, which captures the ever-changing structural and temporal dynamics in TKGs via recurrent event modeling, and models the interactions between entities based on the temporal neighborhood aggregation framework. Further, EvoKG achieves an accurate modeling of event time, using flexible and efficient mechanisms based on neural density estimation. Experiments show that EvoKG outperforms existing methods in terms of effectiveness (up to 77% and 116% more accurate time and link prediction) and efficiency.