GTIN：面向时序图事件与时间联合预测的统一可扩展框架
GTIN: A Unified Scalable Framework for Joint Event and Time Prediction in Temporal Graphs
AI 导读
arXiv 论文提出 GTIN，一个统一可扩展的数学框架，用于在边上有事件发生的时序图中同时预测下一个事件及其发生时间，此前此类联合预测尤其在大规模图上研究较少。该框架能灵活适配多种网络结构和时间动态，在多个数据集上的实验显示其持续优于现有方法，尤其在事件模式不规则和时间依赖复杂的场景中表现突出。
正文 · 原文
Abstract:Temporal graphs are increasingly used to model dynamic systems across diverse domains, including social, financial, 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 yet, especially in large-scale graphs. To address this gap, we propose a scalable unified mathematical framework that captures varying degrees of complexity across temporal graphs with events occurring on the edges. 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 scalable 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.
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.23556 [cs.SI] |
| (or arXiv:2607.23556v3 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.23556 arXiv-issued DOI via DataCite |
Submission history
From: Mohammad Ostadmohammadi [view email]
[v1]
Sun, 26 Jul 2026 09:15:27 UTC (222 KB)
[v2]
Fri, 14 Aug 2026 15:09:18 UTC (218 KB)
[v3]
Mon, 26 Oct 2026 07:24:19 UTC (160 KB)
来源：arXiv cs.AI · arxiv.org