GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs

2026-07-26

AI Summary

Existing approaches struggle to effectively jointly predict both the type and timing of the next event in temporal graphs, particularly when confronted with irregular event patterns and complex temporal dependencies. This work proposes the first unified end-to-end framework that integrates temporal graph neural networks with probabilistic modeling to simultaneously capture event semantics and temporal dynamics. The proposed method flexibly accommodates diverse network structures and evolution patterns, enabling robust performance across varying data characteristics. Extensive experiments on multiple real-world datasets demonstrate that the model significantly outperforms current state-of-the-art approaches, especially in scenarios involving irregular event sequences and intricate dependency structures.

Abstract

Temporal graphs are increasingly used to model dynamic systems in diverse domains such as social networks, financial networks, and traffic networks. Predicting both what the next event will be and when it will occur in these systems is crucial for understanding and anticipating complex behaviors, but has not been studied much. To address this gap, we propose a unified mathematical framework capable of capturing varying degrees of complexity across temporal graphs. Our framework is flexible and expressive enough to accommodate a wide range of network structures and temporal dynamics. Building upon this analysis, we introduce our novel approach for jointly predicting the next event and its occurrence time. Empirical evaluations across multiple datasets demonstrate that our method consistently outperforms existing techniques, particularly in scenarios involving irregular event patterns and complex temporal dependencies. These findings highlight the potential of our framework as a robust foundation for future research in temporal event prediction.

Problem

• temporal graphs
• event prediction
• time prediction
• dynamic systems
• temporal dependencies

Innovation

• temporal graphs
• joint event-time prediction
• unified framework
• temporal dynamics
• event forecasting