Go to ICLR 2026 Conference homepageBLUE: Bi-layer Heterogeneous Graph Fusion Network for Avian Influenza Forecasting
Keywords: Multi-layer graphs, Heterogeneous Graph Network, Avian Influensa Forecasting, Spatio-temporal Forecasting
Abstract: Accurate forecasting of avian influenza outbreaks within wild bird populations requires models that account for complex, multi-scale transmission patterns driven by various factors. Spatio-temporal GNN-based models have recently gained traction for infection forecasting due to their ability to capture relations and flow between spatial regions, but most existing frameworks rely solely on spatial regions and their connections. This overlooks valuable genetic information at the case level, such as cases in one region being genetically descended from strains in another, which is essential for understanding how infectious diseases spread through epidemiological linkages beyond geography. We systemically formulate AIV forecasting problem by proposing a Bi-Layer heterogeneous graph fUsion pipEline (BLUE). This pipeline integrates genetic, spatial, and ecological data to achieve highly accurate outbreak forecasting. It 1) defines heterogeneous graphs from multiple information sources and multiple layers, 2) smooths across relation types, 3) performs fusion while retaining structural patterns, and 4) predicts future outbreaks via an autoregressive graph sequence model that captures transmission dynamics over time. To facilitate further research, we release the \textbf{Avian-US} dataset, the dataset for avian influenza outbreak forecasting in the United States, incorporating genetic, spatial, and ecological data across locations. BLUE achieves superior performance over existing baselines, highlighting the value of incorporating multi-layer information into infectious disease forecasting.
The code is available at: https://anonymous.4open.science/r/BLUE-60F8/README.md.
Primary Area: learning on graphs and other geometries & topologies
Submission Number: 11513
Loading