A networked time series (NETS) is a family of time series on a given graph, one for each node. It has a wide range of applications from intelligent transportation to environment monitoring to smart grid management. An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph. Most existing methods require complete data for training. However, in real-world scenarios, it is not uncommon to have missing data due to sensor malfunction, incomplete sensing coverage, and so on. In this article, we study the problem of NETS prediction with incomplete data. We propose networked time series Imputation Generative Adversarial Network (NETS-ImpGAN), a novel deep learning framework that can be trained on incomplete data with missing values in both history and future. Furthermore, we propose Graph Temporal Attention Networks, which incorporate the attention mechanism to capture both inter-time series and temporal correlations. We conduct extensive experiments on four real-world datasets under different missing patterns and missing rates. The experimental results show that NETS-ImpGAN outperforms existing methods, reducing the Mean Absolute Error by up to 25%.

网络时间序列 (NETS)是给定图上的一系列时间序列，每个节点一个。它具有从智能交通到环境监测到智能电网管理的广泛应用。此类应用程序中的一项重要任务是根据 NETS 的历史值和基础图来预测 NETS 的未来值。大多数现有方法需要完整的数据进行训练。然而，在现实场景中，由于传感器故障、传感覆盖不完整等原因导致数据丢失的情况并不少见。在这篇文章中，我们研究了不完整数据的NETS预测问题。我们提出了网络时间序列插补生成对抗网络（NETS-ImpGAN），这是一种新颖的深度学习框架，可以对历史和未来缺失值的不完整数据进行训练。此外，我们提出了图时间注意力网络，它结合了注意力机制来捕获时间序列和时间相关性。我们在不同缺失模式和缺失率下对四个真实世界数据集进行了广泛的实验。实验结果表明，NETS-ImpGAN 的性能优于现有方法，平均绝对误差降低高达 25%。