DeepTrace: Learning to Optimize Contact Tracing in Epidemic Networks With Graph Neural Networks

作     者：Tan, Chee Wei Yu, Pei-Duo Chen, Siya Poor, H. Vincent 

作者机构：Nanyang Technol Univ Singapore 639798 Singapore Chung Yuan Christian Univ Dept Appl Math Taoyuan City 32023 Taiwan City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Princeton Univ Dept Elect & Comp Engn Princeton NJ 08544 USA 

出 版 物：《IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS》 (IEEE Trans. Signal Inf. Process. Over Netw.)

年 卷 期：2025年第11卷

页      面：97-113页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 

基　　金：U.S. National Science Foundation under RAPID Grant [IIS-2026982] National Science and Technology Council of Taiwan [112-2115-M-033-004-MY2] Hong Kong ITF [ITS/188/20] Singapore Ministry of Education Academic Fund [RG91/22] National Medical Research Council CS-IRG [CIRG24jul-0021] Sayling Wen Cultural & Educational Foundation Faculty Scholarship Institute for Pure and Applied Mathematics Fellowship C3.AI Digital Transformation Institute Princeton Language and Intelligence 

主　　题：COVID-19 Resistance Maximum likelihood estimation Pandemics Contact tracing Graph neural networks Data models Real-time systems Inference algorithms Topology Digital contact tracing contagion source detection maximum likelihood estimation graph neural network online graph exploration 

摘      要：Digital contact tracing aims to curb epidemics by identifying and mitigating public health emergencies through technology. Backward contact tracing, which tracks the sources of infection, proved crucial in places like Japan for identifying COVID-19 infections from superspreading events. This paper presents a novel perspective on digital contact tracing by modeling it as an online graph exploration problem, framing forward and backward tracing strategies as maximum-likelihood estimation tasks that leverage iterative sampling of epidemic network data. The challenge lies in the combinatorial complexity and rapid spread of infections. We introduce DeepTrace, an algorithm based on a Graph Neural Network that iteratively updates its estimations as new contact tracing data is collected, learning to optimize the maximum likelihood estimation by utilizing topological features to accelerate learning and improve convergence. The contact tracing process combines either BFS or DFS to expand the network and trace the infection source, ensuring efficient real-time exploration. Additionally, the GNN model is fine-tuned through a two-phase approach: pre-training with synthetic networks to approximate likelihood probabilities and fine-tuning with high-quality data to refine the model. Using COVID-19 variant data, we illustrate that DeepTrace surpasses current methods in identifying superspreaders, providing a robust basis for a scalable digital contact tracing strategy.