AI RESEARCH

AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

arXiv CS.LG

ArXi:2606.01283v1 Announce Type: new Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based kernels with predefined parameters, which restricts model capacity. Although generic adaptive mechanisms (e.g., Graph Attention Networks) offer flexibility, they often fail to capture the underlying geometric structure, performing worse than distance-based models in data-sparse scenarios.