This study focuses on long-term forecasting (LTF) on continuous-time dynamic graph networks (CTDGNs), which is important for real-world modeling. Existing CTDGNs are effective for modeling temporal graph data due to their ability to capture complex temporal dependencies but perform poorly on LTF due to the substantial requirement for historical data, which is not practical in most cases. To relieve this problem, a most intuitive way is data augmentation. In this study, we propose \textbf{\underline{U}ncertainty \underline{M}asked \underline{M}ix\underline{U}p (UmmU)}: a plug-and-play module that conducts uncertainty estimation to introduce uncertainty into the embedding of intermediate layer of CTDGNs, and perform masked mixup to further enhance the uncertainty of the embedding to make it generalize to more situations. UmmU can be easily inserted into arbitrary CTDGNs without increasing the number of parameters. We conduct comprehensive experiments on three real-world dynamic graph datasets, the results demonstrate that UmmU can effectively improve the long-term forecasting performance for CTDGNs.

翻译：本研究聚焦于连续时间动态图网络（CTDGNs）的长期预测（LTF）问题，这在真实世界建模中具有重要价值。现有CTDGNs虽能有效捕捉复杂的时间依赖性以处理时序图数据，但由于对历史数据的大量需求（这在多数场景下不切实际），它们在长期预测任务中表现较差。为解决此问题，最直观的方法即数据增强。本研究提出**不确定性掩码混合增强（UmmU）**：一种即插即用模块，通过不确定性估计向CTDGNs中间层嵌入引入随机性，并执行掩码混合操作以进一步增强嵌入的不确定性，使其能够泛化至更多场景。UmmU可轻松插入任意CTDGNs中，且不增加参数量。我们在三个真实动态图数据集上开展综合实验，结果表明UmmU能有效提升CTDGNs的长期预测性能。