Continuous-time dynamic graphs (CTDGs) are essential for modeling interconnected, evolving systems. Traditional methods for extracting knowledge from these graphs often depend on feature engineering or deep learning. Feature engineering is limited by the manual and time-intensive nature of crafting features, while deep learning approaches suffer from high inference latency, making them impractical for real-time applications. This paper introduces Deep-Graph-Sprints (DGS), a novel deep learning architecture designed for efficient representation learning on CTDGs with low-latency inference requirements. We benchmark DGS against state-of-the-art feature engineering and graph neural network methods using five diverse datasets. The results indicate that DGS achieves competitive performance while improving inference speed up to 12x compared to other deep learning approaches on our tested benchmarks. Our method effectively bridges the gap between deep representation learning and low-latency application requirements for CTDGs.

翻译：连续时间动态图（CTDGs）对于建模相互关联且不断演化的系统至关重要。从这些图中提取知识的传统方法通常依赖于特征工程或深度学习。特征工程受限于手工设计特征的手动性和耗时性，而深度学习方法则存在推理延迟高的问题，使其难以应用于实时场景。本文提出了Deep-Graph-Sprints（DGS），一种新颖的深度学习架构，专为在具有低延迟推理需求的CTDG上进行高效表示学习而设计。我们使用五个不同的数据集，将DGS与最先进的特征工程和图神经网络方法进行了基准测试。结果表明，DGS在实现具有竞争力的性能的同时，在我们测试的基准上，推理速度相比其他深度学习方法提升了高达12倍。我们的方法有效弥合了深度表示学习与CTDG低延迟应用需求之间的差距。