# The Effect of Quantization in Federated Learning: A R'enyi Differential Privacy Perspective

arXiv: https://arxiv.org/abs/2405.10096 · HTML: https://mlsanity.com/paper/2405.10096/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 16 May 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [cpSGD: Communication-efficient and differentially-private distributed SGD](https://mlsanity.com/paper/1805.10559/) (2018)
- [Distributed Mean Estimation with Limited Communication](https://mlsanity.com/paper/1611.00429/) (2016)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [Differentially Private Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2111.09278/) (2021)
- [GradViT: Gradient Inversion of Vision Transformers](https://mlsanity.com/paper/2203.11894/) (2022)
- [Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design](https://mlsanity.com/paper/2103.14272/) (2021)
- [Binary Federated Learning with Client-Level Differential Privacy](https://mlsanity.com/paper/2308.03320/) (2023)

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

- [From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challenges](https://mlsanity.com/paper/2503.07505/) (2025)
- [On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levels](https://mlsanity.com/paper/2502.18623/) (2025)
- [Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks](https://mlsanity.com/paper/2411.07806/) (2024)
- [DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling](https://mlsanity.com/paper/2509.03472/) (2025)
- [Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference](https://mlsanity.com/paper/2512.15335/) (2025)
- [Communication-Efficient Federated AUC Maximization with Cyclic Client Participation](https://mlsanity.com/paper/2601.01649/) (2026)

## Abstract (arXiv)

Federated Learning (FL) is an emerging paradigm that holds great promise for privacy-preserving machine learning using distributed data. To enhance privacy, FL can be combined with Differential Privacy (DP), which involves adding Gaussian noise to the model weights. However, FL faces a significant challenge in terms of large communication overhead when transmitting these model weights. To address this issue, quantization is commonly employed. Nevertheless, the presence of quantized Gaussian noise introduces complexities in understanding privacy protection. This research paper investigates the impact of quantization on privacy in FL systems. We examine the privacy guarantees of quantized Gaussian mechanisms using R'enyi Differential Privacy (RDP). By deriving the privacy budget of quantized Gaussian mechanisms, we demonstrate that lower quantization bit levels provide improved privacy protection. To validate our theoretical findings, we employ Membership Inference Attacks (MIA), which gauge the accuracy of privacy leakage. The numerical results align with our theoretical analysis, confirming that quantization can indeed enhance privacy protection. This study not only enhances our understanding of the correlation between privacy and communication in FL but also underscores the advantages of quantization in preserving privacy.