GTIN framework predicts both events and timing in dynamic networks

Temporal graphs are increasingly used to model dynamic systems in 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 complex behaviors, but has not been studied much. To address this gap, researchers Mohammad Ostadmohammadi, Sepehr Kazemi, and Hamid R. Rabiee propose GTIN, a unified mathematical framework capable of capturing varying degrees of complexity across temporal graphs. The framework is flexible and expressive enough to accommodate a wide range of network structures and temporal dynamics, building upon a novel approach for jointly predicting the next event and its occurrence time.

Empirical evaluations across multiple datasets demonstrate that GTIN consistently outperforms existing techniques, particularly in scenarios involving irregular event patterns and complex temporal dependencies. These findings highlight the potential of the framework as a robust foundation for future research in temporal event prediction. The paper is available on arXiv (2607.23556) and is relevant to professionals working on predictive analytics in dynamic networks, offering a new state-of-the-art baseline for joint event and time prediction.