mlsanityData to 14 Oct 2026

Graph Kalman Filters

arXiv 2303.12021 ↗First posted 21 Mar 2023cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

The well-known Kalman filters model dynamical systems by relying on state-space representations with the next state updated, and its uncertainty controlled, by fresh information associated with newly observed system outputs. This paper generalizes, for the first time in the literature, Kalman and extended Kalman filters to discrete-time settings where inputs, states, and outputs are represented as attributed graphs whose topology and attributes can change with time. The setup allows us to adapt the framework to cases where the output is a vector or a scalar too (node/graph level tasks). Within the proposed theoretical framework, the unknown state-transition and the readout functions are learned end-to-end along with the downstream prediction task.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

12 of 32 references.

References · 12

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  3. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  4. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  5. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  6. 2019A Gentle Introduction to Deep Learning for Graphscited by 108
  7. 2020Graph Neural Networks in TensorFlow and Keras with Spektralcited by 60
  8. 2020Gated Graph Recurrent Neural Networkscited by 58
  9. 2018Forecasting Time Series with VARMA Recursions on Graphscited by 27
  10. 2021Power Flow Balancing with Decentralized Graph Neural Networkscited by 20
  11. 2016Kernel-based Reconstruction of Space-time Functions on Dynamic Graphscited by 12
  12. 2023Graph State-Space Models and Latent Relational Inferencecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  2. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  3. 2023Sparse Graphical Linear Dynamical Systemscited by 4
  4. 2026PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertaintycited by 1
  5. 2025Spatiotemporal graph neural process for reconstruction, extrapolation, and classification of cardiac trajectoriescited by 0