Who Should I Engage with At What Time? A Missing Event Aware Temporal Graph Neural Network

TL;DR

This paper introduces MTGN, a novel temporal graph neural network that effectively models both observed and missing events to improve future event and timing predictions in dynamic graphs.

Contribution

The paper presents MTGN, a missing event-aware model that jointly captures observed and missing events as coupled temporal point processes, enhancing prediction accuracy.

Findings

MTGN outperforms existing methods with up to 89% more accurate time prediction.

MTGN achieves up to 112% better link prediction accuracy.

Experimental results validate the effectiveness of modeling missing events.

Abstract

Temporal graph neural network has recently received significant attention due to its wide application scenarios, such as bioinformatics, knowledge graphs, and social networks. There are some temporal graph neural networks that achieve remarkable results. However, these works focus on future event prediction and are performed under the assumption that all historical events are observable. In real-world applications, events are not always observable, and estimating event time is as important as predicting future events. In this paper, we propose MTGN, a missing event-aware temporal graph neural network, which uniformly models evolving graph structure and timing of events to support predicting what will happen in the future and when it will happen.MTGN models the dynamic of both observed and missing events as two coupled temporal point processes, thereby incorporating the effects of missing events into the network. Experimental results on several real-world temporal graphs demonstrate that MTGN significantly outperforms existing methods with up to 89% and 112% more accurate time and link prediction. Code can be found on https://github.com/HIT-ICES/TNNLS-MTGN.