AI RESEARCH

Geometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs

arXiv CS.LG

ArXi:2602.18141v2 Announce Type: replace Long-range graph tasks are challenging for Graph Neural Networks (GNNs): global mechanisms such as attention or rewiring schemes can be computationally expensive, while deep local propagation is prone to vanishing gradients, oversmoothing, and oversquashing. The