3 papers
cs.LG2026
Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Distribution shift severely degrades the performance of deep forecasting models. While this issue is well-studied for individual time series, it remains a significant challenge in…
cs.LG2026
Modern Structure-Aware Simplicial Spatiotemporal Neural Network
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Spatiotemporal modeling has evolved beyond simple time series analysis to become fundamental in structural time series analysis. While current research extensively employs graph ne…
cs.LG2026
Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks
Zhaobo Hu, Vincent Gauthier, Mehdi Naima
Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural message passing. In this work, we substitute the traditional Laplacian w…