# Compressed Particle-Based Federated Bayesian Learning and Unlearning

arXiv: https://arxiv.org/abs/2209.07267 · HTML: https://mlsanity.com/paper/2209.07267/

## Key facts

- Cited by 6 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 16 of its 20 references that are in the map.
- First posted on arXiv 14 Sep 2022.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 16 of 16)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm](https://mlsanity.com/paper/1608.04471/) (2016)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks](https://mlsanity.com/paper/2002.10118/) (2020)
- [QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding](https://mlsanity.com/paper/1610.02132/) (2016)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [The Bayesian Learning Rule](https://mlsanity.com/paper/2107.04562/) (2021)
- [Generalized Variational Inference: Three arguments for deriving new Posteriors](https://mlsanity.com/paper/1904.02063/) (2019)
- [Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication](https://mlsanity.com/paper/1805.08768/) (2018)
- [Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent](https://mlsanity.com/paper/2009.06419/) (2020)
- [Partitioned Variational Inference: A unified framework encompassing federated and continual learning](https://mlsanity.com/paper/1811.11206/) (2018)
- [Federated Learning and Wireless Communications](https://mlsanity.com/paper/2005.05265/) (2020)
- [Forget-SVGD: Particle-Based Bayesian Federated Unlearning](https://mlsanity.com/paper/2111.12056/) (2021)
- [DNN-Aided Block Sparse Bayesian Learning for User Activity Detection and Channel Estimation in Grant-Free Non-Orthogonal Random Access](https://mlsanity.com/paper/1910.02953/) (2019)
- [Reconfigurable Intelligent Surface-Aided 6G Massive Access: Coupled Tensor Modeling and Sparse Bayesian Learning](https://mlsanity.com/paper/2206.05427/) (2022)

## Built on by (most cited first, 6 of 6)

- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024)
- [Fast-Convergent Federated Learning via Cyclic Aggregation](https://mlsanity.com/paper/2210.16520/) (2022)
- [A Survey on Federated Unlearning: Challenges and Opportunities](https://mlsanity.com/paper/2403.02437/) (2024)
- [Streamlined Federated Unlearning: Unite as One to Be Highly Efficient](https://mlsanity.com/paper/2412.00126/) (2024)
- [CG-FKAN: Compressed-Grid Federated Kolmogorov-Arnold Networks for Communication Constrained Environment](https://mlsanity.com/paper/2511.01433/) (2025)

## 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.