Predicting the Co-Evolution of Event and Knowledge Graphs

TL;DR

This paper introduces a model for predicting the evolution of knowledge graphs over time by leveraging event data, enabling dynamic updates and improved forecasting in various applications.

Contribution

It presents a novel approach that combines event prediction with knowledge graph embedding to model temporal changes in knowledge graphs.

Findings

Effective in clinical applications

Improves recommendation systems

Works well in sensor network scenarios

Abstract

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models using latent representations of generalized entities. Knowledge graphs are typically treated as static: A knowledge graph grows more links when more facts become available but the ground truth values associated with links is considered time invariant. In this paper we address the issue of knowledge graphs where triple states depend on time. We assume that changes in the knowledge graph always arrive in form of events, in the sense that the events are the gateway to the knowledge graph. We train an event prediction model which uses both knowledge graph background information and information on recent events. By predicting future events, we also predict likely changes in the knowledge graph and thus obtain a model for the evolution of the knowledge graph as well. Our experiments demonstrate that our approach performs well in a clinical application, a recommendation engine and a sensor network application.