PANDORA: Deep graph learning based COVID-19 infection risk level forecasting

TL;DR

PANDORA addresses the challenge of region-level COVID-19 infection risk forecasting by integrating geography-based relations, transportation patterns, and multi-source node attributes into a deep graph learning framework. It leverages higher-order network motifs to capture complex inter-regional connectivity and combines Attribute Feature Tensor and Structural Feature Tensor through three aggregation schemes to predict WHO-based risk levels. Experimental results on static and dynamic US county graphs show that PANDORA achieves higher accuracy and substantially faster convergence than strong baselines, with ablation analyses underscoring the value of each feature group. The work provides a practical, scalable approach for informing targeted public health policies and demonstrates the promise of motif-informed graph learning for epidemic forecasting.

Abstract

COVID-19 as a global pandemic causes a massive disruption to social stability that threatens human life and the economy. Policymakers and all elements of society must deliver measurable actions based on the pandemic's severity to minimize the detrimental impact of COVID-19. A proper forecasting system is arguably important to provide an early signal of the risk of COVID-19 infection so that the authorities are ready to protect the people from the worst. However, making a good forecasting model for infection risks in different cities or regions is not an easy task, because it has a lot of influential factors that are difficult to be identified manually. To address the current limitations, we propose a deep graph learning model, called PANDORA, to predict the infection risks of COVID-19, by considering all essential factors and integrating them into a geographical network. The framework uses geographical position relations and transportation frequency as higher-order structural properties formulated by higher-order network structures (i.e., network motifs). Moreover, four significant node attributes (i.e., multiple features of a particular area, including climate, medical condition, economy, and human mobility) are also considered. We propose three different aggregators to better aggregate node attributes and structural features, namely, Hadamard, Summation, and Connection. Experimental results over real data show that PANDORA outperforms the baseline method with higher accuracy and faster convergence speed, no matter which aggregator is chosen. We believe that PANDORA using deep graph learning provides a promising approach to get superior performance in infection risk level forecasting and help humans battle the COVID-19 crisis.

Figures (10)

• Figure 1: Infection risk level forecasting for certain region.
• Figure 2: Schematic diagram of PANDORA.
• Figure 3: Transmission network motifs employed in this paper.
• Figure 4: Distributions of four kinds of data.
• Figure 5: Distribution normalization in pre-processing data.

Theorems & Definitions (1)

• Definition 1