Active Inference · Paper · 2024

Federated inference and belief sharing

Karl J. Friston, Thomas Parr, Conor Heins, Axel Constant, Daniel Friedman, Takuya Isomura, Chris Fields, Tim Verbelen, Maxwell Ramstead, John Clippinger, Christopher D. Frith

Neuroscience & Biobehavioral Reviews

Catalog Row36
Citation KeyFriedman2024FederatedInferenceBeliefSharing036
Paper FolderAvailable
Platform availability
  • ⬜ Zenodo
  • ⬜ GitHub
  • ⬜ arXiv
  • ⬜ OSF
  • ⬜ HuggingFace
  • ⬜ Software Heritage
  • ⬜ PyPI
  • Full documentation

Overview

Extracted from the local paper documentation when available.

This paper formulates federated inference and belief sharing as a principled approach to distributed intelligence. By extending Active Inference to multi-agent settings, agents maintain local generative models while sharing beliefs through message passing to achieve collective inference. The framework addresses how agents can coordinate without sharing raw observations, preserving privacy while...

federated inferencebelief sharingActive Inferencedistributed intelligencemulti-agent systemsmessage passingcollective cognitionprivacy-preserving inference

Use Notes

Concise findings and methods pulled from README/SKILL documentation.

Findings / Concepts
  • formulates federated inference and belief sharing as a principled approach to distributed intelligence..
  • By extending Active Inference to multi-agent settings, agents maintain local generati....
Methods / Techniques
  • Free energy minimization
  • Bayesian modeling and inference

Citation

Plain-text citation for quick reuse.

Friedman, Daniel Ari. 2024. Federated inference and belief sharing. Neuroscience & Biobehavioral Reviews. DOI: 10.1016/j.neubiorev.2023.105500. URL: https://doi.org/10.1016/j.neubiorev.2023.105500.

Primary source Documentation Full Text Image Gallery BibTeX

Related in Active Inference

Other catalogued works in the same domain.

View all Active Inference works, software & media →