AI RESEARCH
Graph Variate Neural Networks
arXiv CS.LG
•
ArXi:2509.20311v2 Announce Type: replace Modelling dynamically evolving spatio-temporal signals is a prominent challenge in the Graph Neural Network (GNN) literature. Notably, GNNs assume an existing underlying graph structure. While this underlying structure may not always exist or is derived independently from the signal, a temporally evolving functional network can always be constructed from multi-channel data.