mlsanityData to 14 Oct 2026

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

arXiv 2406.18491 ↗First posted 26 Jun 2024cs.LG cs.CR cs.DCcited by 0

Not on the map. Why?

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.

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

20 of 31 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  6. 2019Towards Federated Learning at Scale: System Designcited by 832
  7. 2017Federated Multi-Task Learningcited by 672
  8. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  9. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  10. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  11. 2019Differentially Private Learning with Adaptive Clippingcited by 220
  12. 2018ATOMO: Communication-efficient Learning via Atomic Sparsificationcited by 136
8 more
  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  2. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 107
  3. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
  4. 2018Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learningcited by 77
  5. 2019High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learningcited by 32
  6. 2019One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Themcited by 23
  7. 2024Adaptive Differential Privacy in Federated Learning: A Priority-Based Approachcited by 3
  8. 2024Comments on "Federated Learning with Differential Privacy: Algorithms and Performance Analysis"cited by 1

Built on by

Not cited yet.