# Enhancing Federated Learning with Adaptive Differential Privacy and Priority-Based Aggregation

arXiv: https://arxiv.org/abs/2406.18491 · HTML: https://mlsanity.com/paper/2406.18491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [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)
- [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://mlsanity.com/paper/1804.08333/) (2018)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [ATOMO: Communication-efficient Learning via Atomic Sparsification](https://mlsanity.com/paper/1806.04090/) (2018)
- [Distributed Learning in Wireless Networks: Recent Progress and Future Challenges](https://mlsanity.com/paper/2104.02151/) (2021)
- [UVeQFed: Universal Vector Quantization for Federated Learning](https://mlsanity.com/paper/2006.03262/) (2020)
- [Robust Federated Learning in a Heterogeneous Environment](https://mlsanity.com/paper/1906.06629/) (2019)
- [Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning](https://mlsanity.com/paper/1812.00910/) (2018)
- [High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning](https://mlsanity.com/paper/1910.03865/) (2019)
- [One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them](https://mlsanity.com/paper/1905.04634/) (2019)
- [Adaptive Differential Privacy in Federated Learning: A Priority-Based Approach](https://mlsanity.com/paper/2401.02453/) (2024)
- [Comments on "Federated Learning with Differential Privacy: Algorithms and Performance Analysis"](https://mlsanity.com/paper/2406.05858/) (2024)

## Abstract (arXiv)

Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient updates of deep neural networks) transferred between clients and servers, potentially revealing sensitive local information to adversaries using model inversion attacks. Differential privacy (DP) offers a promising approach to addressing this issue by adding noise to the parameters. On the other hand, heterogeneities in data structure, storage, communication, and computational capabilities of devices can cause convergence problems and delays in developing the global model. A personalized weighted averaging of local parameters based on the resources of each device can yield a better aggregated model in each round. In this paper, to efficiently preserve privacy, we propose a personalized DP framework that injects noise based on clients' relative impact factors and aggregates parameters while considering heterogeneities and adjusting properties. To fulfill the DP requirements, we first analyze the convergence boundary of the FL algorithm when impact factors are personalized and fixed throughout the learning process. We then further study the convergence property considering time-varying (adaptive) impact factors.