# Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

arXiv: https://arxiv.org/abs/2008.07180 · HTML: https://mlsanity.com/paper/2008.07180/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2102.06387/) (2021)
- [MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation](https://mlsanity.com/paper/2110.01406/) (2021)
- [On Large-Cohort Training for Federated Learning](https://mlsanity.com/paper/2106.07820/) (2021)
- [Optimal Algorithms for Mean Estimation under Local Differential Privacy](https://mlsanity.com/paper/2205.02466/) (2022)
- [Stronger Privacy Amplification by Shuffling for R'enyi and Approximate Differential Privacy](https://mlsanity.com/paper/2208.04591/) (2022)
- [Lossless Compression of Efficient Private Local Randomizers](https://mlsanity.com/paper/2102.12099/) (2021)
- [QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning](https://mlsanity.com/paper/2106.00797/) (2021)
- [Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT](https://mlsanity.com/paper/2102.12412/) (2021)
- [Privacy-Aware Compression for Federated Data Analysis](https://mlsanity.com/paper/2203.08134/) (2022)
- [Fast Optimal Locally Private Mean Estimation via Random Projections](https://mlsanity.com/paper/2306.04444/) (2023)
- [Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation](https://mlsanity.com/paper/2111.02356/) (2021)
- [DP-REC: Private & Communication-Efficient Federated Learning](https://mlsanity.com/paper/2111.05454/) (2021)
- [Differentially Private Federated Learning via Reconfigurable Intelligent Surface](https://mlsanity.com/paper/2203.17028/) (2022)
- [Shuffled Differentially Private Federated Learning for Time Series Data Analytics](https://mlsanity.com/paper/2307.16196/) (2023)
- [How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations](https://mlsanity.com/paper/2507.01487/) (2025)

## Abstract (arXiv)

We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learning (FL) framework. Unique challenges to the traditional ERM problem in the context of FL include (i) need to provide privacy guarantees on clients' data, (ii) compress the communication between clients and the server, since clients might have low-bandwidth links, (iii) work with a dynamic client population at each round of communication between the server and the clients, as a small fraction of clients are sampled at each round. To address these challenges we develop (optimal) communication-efficient schemes for private mean estimation for several ℓp spaces, enabling efficient gradient aggregation for each iteration of the optimization solution of the ERM. We also provide lower and upper bounds for mean estimation with privacy and communication constraints for arbitrary ℓp spaces. To get the overall communication, privacy, and optimization performance operation point, we combine this with privacy amplification opportunities inherent to this setup. Our solution takes advantage of the inherent privacy amplification provided by client sampling and data sampling at each client (through Stochastic Gradient Descent) as well as the recently developed privacy framework using anonymization, which effectively presents to the server responses that are randomly shuffled with respect to the clients. Putting these together, we demonstrate that one can get the same privacy, optimization-performance operating point developed in recent methods that use full-precision communication, but at a much lower communication cost, i.e., effectively getting communication efficiency for "free".