# Graph State-Space Models and Latent Relational Inference

Source: [Graph State-Space Models and Latent Relational Inference](<https://www.sota2.com/research/paper/68fa6e5f1e209131cea3f783>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-08T05:00:04.658Z

Authors: Daniele Zambon, Andrea Cini, Cesare Alippi

Published: 2023-01-04T18:15:07.000Z

## Abstract

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. The manuscript aims to fill this gap by matching state-space modeling and spatio-temporal data where the relational information, say the functional graph capturing latent dependencies, is learned directly from time series. In particular, we propose Graph State-Space Models, a novel probabilistic framework that jointly learns state-space dynamics and latent relational structures end-to-end on downstream tasks. The proposed framework generalizes several state-of-the-art methods and, as we show, is effective in extracting meaningful latent relational structures and obtaining accurate forecasts.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Solar Radiation Forecasting on EngRAD (test)](<https://www.sota2.com/research/sota/solar-radiation-forecasting-on-engrad-test.md>): Solar Radiation Forecasting; EngRAD (test); MAE (1-6h): 40.014.

- [1-step ahead forecasting on GPVAR (test)](<https://www.sota2.com/research/sota/1-step-ahead-forecasting-on-gpvar-test.md>): 1-step ahead forecasting; GPVAR (test); MAE: 0.331.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.01741>)

[PDF](<https://arxiv.org/pdf/2301.01741.pdf>)
