mlsanityData to 14 Oct 2026

Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning

arXiv 2506.14251 ↗First posted 17 Jun 2025cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized federated learning (PFL), e.g., the renowned Ditto, strikes a balance between personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). While FL is unaffected by personalized model training, in Ditto, PL depends on the outcome of the FL. However, the clients' concern about their privacy and consequent perturbation of their local models can affect the convergence and (performance) fairness of PL. This paper presents PFL, called DP-Ditto, which is a non-trivial extension of Ditto under the protection of differential privacy (DP), and analyzes the trade-off among its privacy guarantee, model convergence, and performance distribution fairness. We also analyze the convergence upper bound of the personalized models under DP-Ditto and derive the optimal number of global aggregations given a privacy budget. Further, we analyze the performance fairness of the personalized models, and reveal the feasibility of optimizing DP-Ditto jointly for convergence and fairness. Experiments validate our analysis and demonstrate that DP-Ditto can surpass the DP-perturbed versions of the state-of-the-art PFL models, such as FedAMP, pFedMe, APPLE, and FedALA, by over 32.71% in fairness and 9.66% in accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 17 Jun 2025.

Builds on

24 of 52 references.

References · 24

  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  3. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  5. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  6. 2021Towards Personalized Federated Learningcited by 464
  7. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  8. 2019Fair Resource Allocation in Federated Learningcited by 394
  9. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  10. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  11. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  12. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
12 more
  1. 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 75
  2. 2020Federated Learning Meets Multi-objective Optimizationcited by 53
  3. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  4. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  5. 2020Bandit-based Communication-Efficient Client Selection Strategies for Federated Learningcited by 29
  6. 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 25
  7. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  8. 2023Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learningcited by 14
  9. 2022Semi-Synchronous Personalized Federated Learning over Mobile Edge Networkscited by 5
  10. 2023Multi-Carrier NOMA-Empowered Wireless Federated Learning with Optimal Power and Bandwidth Allocationcited by 5
  11. 2023Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channelscited by 5
  12. 2024Decentralized Federated Learning Over Imperfect Communication Channelscited by 5

Built on by

Not cited yet.