Spatiotemporal Kronecker Covariance Neural Networks

The paper introduces the Kronecker coVariance Neural Network (KVNN), a temporal graph neural network that models spatiotemporal covariance matrices as sums of Kronecker products, decoupling spatial and temporal dependencies. KVNNs perform filtering on spatial and temporal components, enabling expressive processing, rigorous spectral analysis, and provable stability to finite-sample estimation errors. Experiments on five real-world datasets show that KVNNs deliver strong forecasting performance with fewer trainable parameters than competing methods and maintain consistency under estimation noise.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.