In this paper, we introduce Temporal Multiresolution Graph Neural Networks
(TMGNN), the first architecture that both learns to construct the multiscale
and multiresolution graph structures and incorporates the time-series signals
to capture the temporal changes of the dynamic graphs. We have applied our
proposed model to the task of predicting future spreading of epidemic and
pandemic based on the historical time-series data collected from the actual
COVID-19 pandemic and chickenpox epidemic in several European countries, and
have obtained competitive results in comparison to other previous
state-of-the-art temporal architectures and graph learning algorithms. We have
shown that capturing the multiscale and multiresolution structures of graphs is
important to extract either local or global information that play a critical
role in understanding the dynamic of a global pandemic such as COVID-19 which
started from a local city and spread to the whole world. Our work brings a
promising research direction in forecasting and mitigating future epidemics and
pandemics.

本文介绍了 Temporal Multiresolution Graph Neural Networks（TMGNN）的建立，这是一种同时学习构造多尺度和多分辨率图结构，并将时间序列信号整合到动态图中捕获时间变化的第一种结构，将其应用于基于欧洲几个国家实际搜集的 COVID-19 爆发和水痘疫情的历史时间序列数据进行流行病和疫情预测，与其他先前最先进的时间结构和图形学习算法相比，取得了有竞争力的结果。我们证明了捕捉图形的多尺度和多分辨率结构对于提取局部或全局信息对于理解 COVID-19 等全球大流行病的动态是至关重要的，该大流行病从一个城市开始，迅速蔓延至全球。我们的工作为预测和减轻未来的流行病和疫情带来了有希望的研究方向。