mlsanityData to 14 Oct 2026

Bayesian Variational Federated Learning and Unlearning in Decentralized Networks

arXiv 2104.03834 ↗First posted 8 Apr 2021cs.LG cs.DC stat.MLcited by 9

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions. Upon the completion of collaborative training, an agent may decide to exercise her legal "right to be forgotten", which calls for her contribution to the jointly trained model to be deleted and discarded. This paper studies federated learning and unlearning in a decentralized network within a Bayesian framework. It specifically develops federated variational inference (VI) solutions based on the decentralized solution of local free energy minimization problems within exponential-family models and on local gossip-driven communication. The proposed protocols are demonstrated to yield efficient unlearning mechanisms.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 13 of its 19 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

13 of 19 references.

References · 13

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  5. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  6. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 283
  7. 2020Variational Bayesian Unlearningcited by 117
  8. 2017Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Modelscited by 65
  9. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  10. 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 35
  11. 2018Partitioned Variational Inference: A unified framework encompassing federated and continual learningcited by 29
  12. 2017A Brief Introduction to Machine Learning for Engineerscited by 20
1 more
  1. 2020Private Weighted Random Walk Stochastic Gradient Descentcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 1; 2025: 2; 2026: 1.

9 papers.

  1. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directionscited by 63
  2. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 51
  3. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 27
  4. 2022Knowledge Removal in Sampling-based Bayesian Inferencecited by 21
  5. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearningcited by 16
  6. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 13
  7. 2025Targeted Forgetting of Image Subgroups in CLIP Modelscited by 6
  8. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0cited by 0
  9. 2026Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Compressed Particle-Based Federated Bayesian Learning and Unlearning
  2. 2026A Secure and Private Distributed Bayesian Federated Learning Design
  3. 2024Communication Efficient and Provable Federated Unlearning
  4. 2025Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications
  5. 2026Robust Federated Q-Learning with Almost No Communication
  6. 2026Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning
  7. 2023Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling
  8. 2022Communication-Efficient Federated Learning With Data and Client Heterogeneity