mlsanityData to 7 Oct 2026

Compressed Particle-Based Federated Bayesian Learning and Unlearning

arXiv 2209.07267 ↗First posted 14 Sep 2022cs.LG eess.SPcited by 5

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

Abstract (arXiv)

Conventional frequentist FL schemes are known to yield overconfident decisions. Bayesian FL addresses this issue by allowing agents to process and exchange uncertainty information encoded in distributions over the model parameters. However, this comes at the cost of a larger per-iteration communication overhead. This letter investigates whether Bayesian FL can still provide advantages in terms of calibration when constraining communication bandwidth. We present compressed particle-based Bayesian FL protocols for FL and federated "unlearning" that apply quantization and sparsification across multiple particles. The experimental results confirm that the benefits of Bayesian FL are robust to bandwidth constraints.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 16 of its 20 references that are in the map. First posted on arXiv 14 Sep 2022.

Builds on

16 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearning23 Nov

Other references · 15

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  3. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  4. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  5. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  6. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  7. 2020Variational Bayesian Unlearningcited by 114
  8. 2021The Bayesian Learning Rulecited by 95
  9. 2019Generalized Variational Inference: Three arguments for deriving new Posteriorscited by 57
  10. 2018Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communicationcited by 51
  11. 2020Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descentcited by 34
  12. 2018Partitioned Variational Inference: A unified framework encompassing federated and continual learningcited by 29
3 more
  1. 2020Federated Learning and Wireless Communicationscited by 27
  2. 2019DNN-Aided Block Sparse Bayesian Learning for User Activity Detection and Channel Estimation in Grant-Free Non-Orthogonal Random Accesscited by 2
  3. 2022Reconfigurable Intelligent Surface-Aided 6G Massive Access: Coupled Tensor Modeling and Sparse Bayesian Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 3; 2025: 1.

5 papers.

  1. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metricscited by 25
  2. 2022Fast-Convergent Federated Learning via Cyclic Aggregationcited by 6
  3. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  4. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficientcited by 0
  5. 2025CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environmentcited by 0