# Differentially-Private Multi-Tier Federated Learning

arXiv: https://arxiv.org/abs/2401.11592 · HTML: https://mlsanity.com/paper/2401.11592/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 21 Jan 2024.

## Builds on (most cited first, 10 of 10)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [On the Convergence of Local Descent Methods in Federated Learning](https://mlsanity.com/paper/1910.14425/) (2019)
- [Local and Central Differential Privacy for Robustness and Privacy in Federated Learning](https://mlsanity.com/paper/2009.03561/) (2020)
- [Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy](https://mlsanity.com/paper/2106.13673/) (2021)
- [When Machine Learning Meets Privacy: A Survey and Outlook](https://mlsanity.com/paper/2011.11819/) (2020)
- [Delay-Aware Hierarchical Federated Learning](https://mlsanity.com/paper/2303.12414/) (2023)
- [Hierarchical Federated Learning with Privacy](https://mlsanity.com/paper/2206.05209/) (2022)

## Abstract (arXiv)

While federated learning (FL) eliminates the transmission of raw data over a network, it is still vulnerable to privacy breaches from the communicated model parameters. In this work, we propose Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M^2FDP), a DP-enhanced FL methodology for jointly optimizing privacy and performance in hierarchical networks. One of the key concepts of M^2FDP is to extend the concept of HDP towards Multi-Tier Differential Privacy (MDP), while also adapting DP noise injection at different layers of an established FL hierarchy -- edge devices, edge servers, and cloud servers -- according to the trust models within particular subnetworks. We conduct a comprehensive analysis of the convergence behavior of M^2FDP, revealing conditions on parameter tuning under which the training process converges sublinearly to a finite stationarity gap that depends on the network hierarchy, trust model, and target privacy level. Subsequent numerical evaluations demonstrate that M^2FDP obtains substantial improvements in these metrics over baselines for different privacy budgets, and validate the impact of different system configurations.