mlsanityData to 14 Oct 2026

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning

arXiv 2202.05318 ↗First posted 10 Feb 2022stat.ML cs.CR cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Large-scale machine learning systems often involve data distributed across a collection of users. Federated learning algorithms leverage this structure by communicating model updates to a central server, rather than entire datasets. In this paper, we study stochastic optimization algorithms for a personalized federated learning setting involving local and global models subject to user-level (joint) differential privacy. While learning a private global model induces a cost of privacy, local learning is perfectly private. We provide generalization guarantees showing that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

33 of 42 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  6. 2017Federated Multi-Task Learningcited by 672
  7. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  8. 2019Federated Learning with Personalization Layerscited by 541
  9. 2020Adaptive Personalized Federated Learningcited by 358
  10. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
  11. 2021A Field Guide to Federated Optimizationcited by 315
  12. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
21 more
  1. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
  2. 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
  3. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  4. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  5. 2020Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 153
  6. 2020Is Local SGD Better than Minibatch SGD?cited by 151
  7. 2019Federated Evaluation of On-device Personalizationcited by 147
  8. 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 142
  9. 2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
  10. 2021Federated Reconstruction: Partially Local Federated Learningcited by 79
  11. 2016Decentralized Collaborative Learning of Personalized Models over Networkscited by 76
  12. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  13. 2021Learning with User-Level Privacycited by 72
  14. 2020Federated Mutual Learningcited by 71
  15. 2018Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passescited by 69
  16. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  17. 2019Differentially Private Meta-Learningcited by 41
  18. 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
  19. 2013Private Matchings and Allocationscited by 23
  20. 2020Federated Residual Learningcited by 23
  21. 2021Private Multi-Task Learning: Formulation and Applications to Federated Learningcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 7; 2025: 6; 2026: 3.

23 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  2. 2023Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learningcited by 29
  3. 2023On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximationcited by 16
  4. 2024Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updatescited by 14
  5. 2023Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learningcited by 13
  6. 2024Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-offcited by 7
  7. 2023Balancing Privacy Protection and Interpretability in Federated Learningcited by 6
  8. 2024Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clientscited by 5
  9. 2025Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Modelscited by 5
  10. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  11. 2023Collaborative Learning From Distributed Data With Differentially Private Synthetic Twin Datacited by 1
  12. 2024Semi-Variance Reduction for Fair Federated Learningcited by 1
11 more
  1. 2024Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guaranteescited by 1
  2. 2024DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimizationcited by 0
  3. 2024FedTLU: Federated Learning with Targeted Layer Updatescited by 0
  4. 2025Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updatescited by 0
  5. 2025An Empirical Study of the Impact of Federated Learning on Machine Learning Model Accuracycited by 0
  6. 2025Personalized Federated Training of Diffusion Models with Privacy Guaranteescited by 0
  7. 2025Personalized and Resilient Distributed Learning Through Opinion Dynamicscited by 0
  8. 2025ADP-VRSGP: Decentralized Learning with Adaptive Differential Privacy via Variance-Reduced Stochastic Gradient Pushcited by 0
  9. 2026FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharingcited by 0
  10. 2026Tackling Privacy Heterogeneity in Differentially Private Federated Learningcited by 0
  11. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0