Graph State-Space Models and Latent Relational Inference

ArXi:2301.01741v2 Announce Type: replace State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation is usually a vector without any explicit structure. Relational inductive biases, e.g., associated with dependencies among input signals and state representations, are not explicitly exploited during processing, leaving unattended opportunities for effective modeling.