Identifying Asymptomatic Nodes in Network Epidemics using Graph Neural Networks

2025-10-02

AI Summary

In network epidemiology, asymptomatic infected individuals—undetectable yet continuously infectious—pose significant challenges for surveillance and intervention. This paper addresses the problem of identifying such “infected-but-observed-as-susceptible” nodes in the classic SI model. We propose a supervised graph neural network (GNN)-based framework that leverages only the network topology and a sparse set of observed infected nodes to learn node representations and infer true infection status. Our key contributions are threefold: (1) high-accuracy classification of asymptomatic individuals without large-scale testing; (2) strong generalization across diverse network types (e.g., scale-free, small-world) and scales; and (3) robust performance under extremely low observation rates (e.g., <10% of infected nodes observable). Extensive experiments on synthetic and real-world networks demonstrate that our method significantly outperforms conventional heuristic and non-graph-aware baselines, establishing a new state-of-the-art for asymptomatic node detection in epidemic modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Infected individuals in some epidemics can remain asymptomatic while still carrying and transmitting the infection. These individuals contribute to the spread of the epidemic and pose a significant challenge to public health policies. Identifying asymptomatic individuals is critical for measuring and controlling an epidemic, but periodic and widespread testing of healthy individuals is often too costly. This work tackles the problem of identifying asymptomatic individuals considering a classic SI (Susceptible-Infected) network epidemic model where a fraction of the infected nodes are not observed as infected (i.e., their observed state is identical to susceptible nodes). In order to classify healthy nodes as asymptomatic or susceptible, a Graph Neural Network (GNN) model with supervised learning is adopted where a set of node features are built from the network with observed infected nodes. The approach is evaluated across different network models, network sizes, and fraction of observed infections. Results indicate that the proposed methodology is robust across different scenarios, accurately identifying asymptomatic nodes while also generalizing to different network sizes and fraction of observed infections.

Problem

• Identifying asymptomatic individuals in network epidemics
• Using Graph Neural Networks to classify unobserved infections
• Developing robust methodology for epidemic control

Innovation

• GNN model classifies asymptomatic nodes via supervised learning
• Node features constructed from network with observed infections
• Methodology robust across network sizes and infection fractions