# FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection

arXiv: https://arxiv.org/abs/2509.10041 · HTML: https://mlsanity.com/paper/2509.10041/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 80 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [FetchSGD: Communication-Efficient Federated Learning with Sketching](https://mlsanity.com/paper/2007.07682/) (2020)
- [Protection Against Reconstruction and Its Applications in Private Federated Learning](https://mlsanity.com/paper/1812.00984/) (2018)
- [Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2111.14213/) (2021)
- [Global Convergence of ADMM in Nonconvex Nonsmooth Optimization](https://mlsanity.com/paper/1511.06324/) (2015)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Federated Learning for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2306.05980/) (2023)
- [Differentially Private Meta-Learning](https://mlsanity.com/paper/1909.05830/) (2019)
- [Local Differential Privacy and Its Applications: A Comprehensive Survey](https://mlsanity.com/paper/2008.03686/) (2020)
- [The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning](https://mlsanity.com/paper/2203.03761/) (2022)
- [Cross-Silo Federated Learning: Challenges and Opportunities](https://mlsanity.com/paper/2206.12949/) (2022)
- [FS-Real: Towards Real-World Cross-Device Federated Learning](https://mlsanity.com/paper/2303.13363/) (2023)
- [Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation](https://mlsanity.com/paper/2304.01541/) (2023)
- [FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching](https://mlsanity.com/paper/2008.04975/) (2020)
- [Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise](https://mlsanity.com/paper/2211.15893/) (2022)
- [An Introduction to Johnson-Lindenstrauss Transforms](https://mlsanity.com/paper/2103.00564/) (2021)
- [Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data](https://mlsanity.com/paper/2006.06983/) (2020)
- [Deep Leakage from Model in Federated Learning](https://mlsanity.com/paper/2206.04887/) (2022)
- [On the Convergence of Alternating Direction Lagrangian Methods for Nonconvex Structured Optimization Problems](https://mlsanity.com/paper/1409.8033/) (2014)
- [Learning of Gaussian Processes in Distributed and Communication Limited Systems](https://mlsanity.com/paper/1705.02627/) (2017)

## Abstract (arXiv)

Federated learning (FL) enables collaborative model training without centralizing data, but exchanging high-dimensional updates can expose sensitive information and incur substantial communication costs. We present FedRP, a communication-efficient method combining Gaussian random projection with consensus optimization based on the alternating direction method of multipliers (ADMM). In each round, clients project their model parameters into an m-dimensional space using a shared random matrix hidden from the server, which aggregates only compressed representations. We establish a high-probability guarantee linking projected-space consensus to proximity among client models and derive an (ε,δ)-differential privacy guarantee for each release under bounded ℓ2-sensitivity and a positive lower bound on parameter norms. With randomized parameter vectors and the projection matrix also limits information available to common reconstruction attacks. Experiments on MNIST and CIFAR-10 with LeNet-5 and a custom convolutional network show that FedRP achieves accuracy comparable to FedAvg and consistently exposes noise-perturbed privacy via FedAvg. Because clients transmit m rather than n values per round, FedRP reduces communication by orders of magnitude when m ll n. The results demonstrate a favorable trade-off among accuracy, privacy, and communication efficiency. Code is available at https://github.com/mhnarimani/FedRP