通过数据增广提升基于连续时间动态图网络的长期预测性能（英文版）

英文标题：Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation中文摘要：该研究提出了一种基于数据增强的 plug-and-play 模块 UmmU，采用不确定性估计和遮盖式 Mixup 技术来增加嵌入层的不确定性，进一步增强嵌入层的泛化能力，结果表明 UmmU 可以有效提高连续时间动态图网络的长期预测性能。英文摘要：This study focuses on long-term forecasting (LTF) on continuous-time dynamicgraph networks (CTDGNs), which is important for real-world modeling. ExistingCTDGNs are effective for modeling temporal graph data due to their ability tocapture complex temporal depe