mlsanityData to 7 Oct 2026

Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning

arXiv 2506.20413 ↗First posted 25 Jun 2025cs.LG cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

The growing adoption of Artificial Intelligence (AI) in Internet of Things (IoT) ecosystems has intensified the need for personalized learning methods that can operate efficiently and privately across heterogeneous, resource-constrained devices. However, enabling effective personalized learning in decentralized settings introduces several challenges, including efficient knowledge transfer between clients, protection of data privacy, and resilience against poisoning attacks. In this paper, we address these challenges by developing P4 (Personalized, Private, Peer-to-Peer) -- a method designed to deliver personalized models for resource-constrained IoT devices while ensuring differential privacy and robustness against poisoning attacks. Our solution employs a lightweight, fully decentralized algorithm to privately detect client similarity and form collaborative groups. Within each group, clients leverage differentially private knowledge distillation to co-train their models, maintaining high accuracy while ensuring robustness to the presence of malicious clients. We evaluate P4 on popular benchmark datasets using both linear and CNN-based architectures across various heterogeneity settings and attack scenarios. Experimental results show that P4 achieves 5% to 30% higher accuracy than leading differentially private peer-to-peer approaches and maintains robustness with up to 30% malicious clients. Additionally, we demonstrate its practicality by deploying it on resource-constrained devices, where collaborative training between two clients adds only ~7 seconds of overhead.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 66 of its 98 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

66 of 98 references.

References · 66

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  4. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  5. 2021Model-Contrastive Federated Learningcited by 762
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  9. 2017Deep Mutual Learningcited by 621
  10. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  11. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  12. 2020An Efficient Framework for Clustered Federated Learningcited by 505
38 more
  1. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  2. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  3. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  4. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  5. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  6. 2019Robust Aggregation for Federated Learningcited by 314
  7. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  8. 2019Can You Really Backdoor Federated Learning?cited by 250
  9. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  10. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  11. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 233
  12. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  13. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  14. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  15. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  16. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  17. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  18. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
  19. 2021Decentralized Federated Averagingcited by 114
  20. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  21. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  22. 2019Peer-to-peer Federated Learning on Graphscited by 85
  23. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  24. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  25. 2020Federated Mutual Learningcited by 70
  26. 2019On-Device Machine Learning: An Algorithms and Learning Theory Perspectivecited by 63
  27. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 56
  28. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  29. 2014Deep Roto-Translation Scattering for Object Classificationcited by 49
  30. 2019Free-riders in Federated Learning: Attacks and Defensescited by 48
  31. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  32. 2024Byzantine-Robust Decentralized Federated Learningcited by 47
  33. 2023Improving the Model Consistency of Decentralized Federated Learningcited by 45
  34. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  35. 2019Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphscited by 34
  36. 2021Implicit Gradient Alignment in Distributed and Federated Learningcited by 29
  37. 2022Byzantine-Robust Decentralized Learning via ClippedGossipcited by 29
  38. 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 28

50 most cited of 66 All 66 (JSON)

Built on by

Not cited yet.