mlsanityData to 7 Oct 2026

A visual introduction to Gaussian Belief Propagation

arXiv 2107.02308 ↗First posted 5 Jul 2021cs.AI cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

In this article, we present a visual introduction to Gaussian Belief Propagation (GBP), an approximate probabilistic inference algorithm that operates by passing messages between the nodes of arbitrarily structured factor graphs. A special case of loopy belief propagation, GBP updates rely only on local information and will converge independently of the message schedule. Our key argument is that, given recent trends in computing hardware, GBP has the right computational properties to act as a scalable distributed probabilistic inference framework for future machine learning systems.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 19 of its 58 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

19 of 58 references.

References · 19

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  2. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  6. 2013Expectation Propagation for approximate Bayesian inferencecited by 172
  7. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  8. 2017The Consciousness Priorcited by 105
  9. 2013Loopy Belief Propagation for Approximate Inference: An Empirical Studycited by 76
  10. 2020Neural Enhanced Belief Propagation on Factor Graphscited by 55
  11. 2017Continuous-Time Gaussian Process Motion Planning via Probabilistic Inferencecited by 49
  12. 2018FutureMapping: The Computational Structure of Spatial AI Systemscited by 35
7 more
  1. 2020Belief Propagation Neural Networkscited by 31
  2. 2019FutureMapping 2: Gaussian Belief Propagation for Spatial AIcited by 16
  3. 2020Bundle Adjustment on a Graph Processorcited by 15
  4. 2019A Survey on Graph Processing Accelerators: Challenges and Opportunitiescited by 5
  5. 2020Ego-Motion Alignment from Face Detections for Collaborative Augmented Realitycited by 1
  6. 2020Fundamental Linear Algebra Problem of Gaussian Inferencecited by 1
  7. 2021Differentiable Nonparametric Belief Propagationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 1; 2024: 3; 2025: 1; 2026: 3.

12 papers.

  1. 2022A Robot Web for Distributed Many-Device Localisationcited by 8
  2. 2022Distributing Collaborative Multi-Robot Planning with Gaussian Belief Propagationcited by 4
  3. 2021Incremental Abstraction in Distributed Probabilistic SLAM Graphscited by 3
  4. 2024Gaussian Ensemble Belief Propagation for Efficient Inference in High-Dimensional Systemscited by 2
  5. 2026Compositional Visual Planning via Inference-Time Diffusion Scalingcited by 2
  6. 2023Learning in Deep Factor Graphs with Gaussian Belief Propagationcited by 1
  7. 2026A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computingcited by 1
  8. 2022See What the Robot Can't See: Learning Cooperative Perception for Visual Navigationcited by 0
  9. 2024PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagationcited by 0
  10. 2024Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAMcited by 0
  11. 2025Aggregating Direct and Indirect Neighbors through Graph Linear Transformationscited by 0
  12. 2026PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimationcited by 0