Institution profile

South China Normal University

Academic institutionasia · cn
Official website
Research library206linked papers
Opportunities0open roles
Selected work

Representative Papers

Epidemiology-informed Graph Neural Network for Heterogeneity-aware Epidemic Forecasting

Nov 26, 2024arXiv.org

Existing spatiotemporal graph neural networks (STGNNs) for epidemic forecasting assume that regions with similar historical features exhibit consistent future infection trends, overlooking mechanism heterogeneity induced by unobserved factors—such as healthcare capacity, viral variants, and human mobility—across geographic and temporal dimensions. To address this, we propose Mechanism-Aware STGNN (HeatGNN), the first framework to embed SEIR-inspired mechanistic models into graph neural networks, enabling learnable and interpretable, location-specific propagation modeling via a time-varying mechanism affinity graph. Our method integrates dynamic graph learning with heterogeneous spatiotemporal graph convolution, ensuring linear scalability. Extensive experiments on three benchmark datasets demonstrate statistically significant improvements over state-of-the-art baselines, validating HeatGNN’s capability to effectively capture mechanism heterogeneity and its feasibility for large-scale deployment.

3 citationsRead paper

Geometric Flow enhanced Graph Coarsening

Sep 13, 2026

本文提出了一种新的图池化方法RicciPool,通过引入Ollivier-Ricci曲率和流公式来重新加权边权重,并利用谱聚类技术学习新的聚类分配矩阵,从而解决现有方法忽略高阶互连信息的问题。

0 citationsRead paper
Recent publications

Latest Papers

Geometric Flow enhanced Graph Coarsening

Sep 13, 2026

本文提出了一种新的图池化方法RicciPool,通过引入Ollivier-Ricci曲率和流公式来重新加权边权重,并利用谱聚类技术学习新的聚类分配矩阵,从而解决现有方法忽略高阶互连信息的问题。

0 citationsRead paper