当前位置: X-MOL 学术arXiv.cs.SI › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks
arXiv - CS - Social and Information Networks Pub Date : 2020-07-06 , DOI: arxiv-2007.03113
Amol Kapoor, Xue Ben, Luyang Liu, Bryan Perozzi, Matt Barnes, Martin Blais, Shawn O'Banion

In this work, we examine a novel forecasting approach for COVID-19 case prediction that uses Graph Neural Networks and mobility data. In contrast to existing time series forecasting models, the proposed approach learns from a single large-scale spatio-temporal graph, where nodes represent the region-level human mobility, spatial edges represent the human mobility based inter-region connectivity, and temporal edges represent node features through time. We evaluate this approach on the US county level COVID-19 dataset, and demonstrate that the rich spatial and temporal information leveraged by the graph neural network allows the model to learn complex dynamics. We show a 6% reduction of RMSLE and an absolute Pearson Correlation improvement from 0.9978 to 0.998 compared to the best performing baseline models. This novel source of information combined with graph based deep learning approaches can be a powerful tool to understand the spread and evolution of COVID-19. We encourage others to further develop a novel modeling paradigm for infectious disease based on GNNs and high resolution mobility data.

中文翻译:

使用时空图神经网络检查 COVID-19 预测

在这项工作中,我们研究了一种使用图神经网络和移动性数据的 COVID-19 病例预测的新预测方法。与现有的时间序列预测模型相比,所提出的方法从单个大规模时空图中学习,其中节点表示区域级别的人员流动,空间边表示基于区域间连接的人员移动,时间边表示节点特征随时间变化。我们在美国县级 COVID-19 数据集上评估了这种方法,并证明了图神经网络利用的丰富时空信息使模型能够学习复杂的动态。与性能最佳的基线模型相比,我们显示 RMSLE 降低了 6%,并且绝对 Pearson 相关性从 0.9978 提高到 0.998。这种新颖的信息来源与基于图的深度学习方法相结合,可以成为了解 COVID-19 传播和演变的强大工具。我们鼓励其他人进一步开发基于 GNN 和高分辨率移动数据的传染病新建模范式。
更新日期:2020-07-08
down
wechat
bug