Promoting Fair Vaccination Strategies Through Influence Maximization: A Case Study on COVID-19 Spread

TL;DR

This study proposes a novel approach that utilizes influence maximization on mobility networks to develop vaccination strategies which incorporate demographic fairness, and demonstrates the effectiveness of the proposed approach in reducing disease transmission and promoting fairness in vaccination distribution.

Abstract

The aftermath of the Covid-19 pandemic saw more severe outcomes for racial minority groups and economically-deprived communities. Such disparities can be explained by several factors, including unequal access to healthcare, as well as the inability of low income groups to reduce their mobility due to work or social obligations. Moreover, senior citizens were found to be more susceptible to severe symptoms, largely due to age-related health reasons. Adapting vaccine distribution strategies to consider a range of demographics is therefore essential to address these disparities. In this study, we propose a novel approach that utilizes influence maximization (IM) on mobility networks to develop vaccination strategies which incorporate demographic fairness. By considering factors such as race, social status, age, and associated risk factors, we aim to optimize vaccine distribution to achieve various fairness definitions for one or more protected attributes at a time. Through extensive experiments conducted on Covid-19 spread in three major metropolitan areas across the United States, we demonstrate the effectiveness of our proposed approach in reducing disease transmission and promoting fairness in vaccination distribution.

Figures (4)

• Figure 1: The reduction in mobility from before lockdown to during lockdown per racial groups and income groups in Philadelphia, New York and Chicago metropolitan areas. For all three areas, lower income groups and racial minorities belonging to lower income groups (see Fig. \ref{['fig:raceincome']}) were less able to reduce their mobility as quickly when transitioning to lockdown.
• Figure 2: Racial distributions of CBGs grouped by their median income. Income groups are determined by quartiles of the median income distribution. Results are for three MSAs: Philadelphia, New York and Chicago.
• Figure 3: Performance measured by percentage decrease in infections (top), and percentage decrease in risk-weighted infections, i.e. with a weighted penalty of infecting older communities (bottom), compared to not vaccinating. Higher is better for both metrics.
• Figure 4: The KL-divergence scores measure fair treatment (red) and fair outcomes (blue) with respect to racial groups (left) and income groups (right). Lower $D_{KL}$ corresponds to better fairness for both metrics.