Higher-order Interaction Matters: Dynamic Hypergraph Neural Networks for Epidemic Modeling

2025-03-25

AI Summary

Traditional epidemiological models (e.g., SIR, GCN) are constrained by graph structures’ limited capacity to represent higher-order, dynamic, and multi-granular interactions inherent in human contact networks. To address this, we propose EpiDHGNN—the first dynamic hypergraph neural network framework specifically designed for epidemic modeling. It explicitly encodes location-individual dual-granularity hyperedges to capture multi-source contact trajectories and establishes an end-to-end differentiable prediction architecture. Our key contribution is the first integration of dynamic hypergraphs into infectious disease modeling, thereby overcoming the binary-relation limitation of conventional graph-based approaches. Extensive experiments on both real-world and synthetic datasets demonstrate that EpiDHGNN significantly outperforms baseline models—including SIR, GCN, and GAT—on epidemic spread forecasting and source identification tasks, achieving an 18.7% reduction in mean absolute error (MAE).

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
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

The ongoing need for effective epidemic modeling has driven advancements in capturing the complex dynamics of infectious diseases. Traditional models, such as Susceptible-Infected-Recovered, and graph-based approaches often fail to account for higher-order interactions and the nuanced structure pattern inherent in human contact networks. This study introduces a novel Human Contact-Tracing Hypergraph Neural Network framework tailored for epidemic modeling called EpiDHGNN, leveraging the capabilities of hypergraphs to model intricate, higher-order relationships from both location and individual level. Both real-world and synthetic epidemic data are used to train and evaluate the model. Results demonstrate that EpiDHGNN consistently outperforms baseline models across various epidemic modeling tasks, such as source detection and forecast, by effectively capturing the higher-order interactions and preserving the complex structure of human interactions. This work underscores the potential of representing human contact data as hypergraphs and employing hypergraph-based methods to improve epidemic modeling, providing reliable insights for public health decision-making.

Problem

• Modeling higher-order interactions in epidemic dynamics
• Improving epidemic forecasting and source detection accuracy
• Capturing complex human contact network structures

Innovation

• Dynamic hypergraph neural networks for epidemics
• Captures higher-order human contact interactions
• Outperforms traditional epidemic modeling methods