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

• URL: http://arxiv.org/abs/2506.20413v1
• Date: Wed, 25 Jun 2025 13:27:36 GMT
• Title: Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning
• Authors: Mohammad Mahdi Maheri, Denys Herasymuk, Hamed Haddadi,
• Abstract summary: We develop P4 (Personalized, Private, Peer-to-Peer) to deliver personalized models for resource-constrained IoT devices.<n>Our solution employs a lightweight, fully decentralized algorithm to privately detect client similarity and form collaborative groups.<n>P4 achieves 5% to 30% higher accuracy than leading differentially private peer-to-peer approaches and maintains robustness with up to 30% malicious clients.
• Score: 5.881825061973424
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Blockchain-Enabled Privacy-Preserving Second-Order Federated Edge Learning in Personalized Healthcare [1.859970493489417]
  Federated learning (FL) has attracted increasing attention to security and privacy challenges in traditional cloud-centric machine learning models.<n>First-order FL approaches face several challenges in personalized model training due to heterogeneous non-independent and identically distributed (non-iid) data.<n>Recently, second-order FL approaches maintain the stability and consistency of non-iid datasets while improving personalized model training.
  arXiv  Detail & Related papers  (2025-05-31T06:41:04Z)
• PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data [47.745068077169954]
  Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy.<n>We propose Privacy-Adaptive Clustered Federated Learning (PA-CFL) tailored for demand forecasting on heterogeneous retail data.
  arXiv  Detail & Related papers  (2025-03-15T18:07:54Z)
• Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients [60.22876915395139]
  This paper studies a challenging robust federated learning task with model heterogeneous and data corrupted clients.<n>Data corruption is unavoidable due to factors such as random noise, compression artifacts, or environmental conditions in real-world deployment.<n>We propose a novel Robust Asymmetric Heterogeneous Federated Learning framework to address these issues.
  arXiv  Detail & Related papers  (2025-03-12T09:52:04Z)
• Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case [0.30723404270319693]
  This paper introduces a client selection framework for Federated Learning (FL) that incorporates differential privacy and fault tolerance.<n>Results demonstrate up to a 7% improvement in accuracy and a 25% reduction in training time compared to the FedL2P approach.
  arXiv  Detail & Related papers  (2025-01-25T02:50:46Z)
• Federated Instruction Tuning of LLMs with Domain Coverage Augmentation [87.49293964617128]
  Federated Domain-specific Instruction Tuning (FedDIT) utilizes limited cross-client private data together with various strategies of instruction augmentation.<n>We propose FedDCA, which optimize domain coverage through greedy client center selection and retrieval-based augmentation.<n>For client-side computational efficiency and system scalability, FedDCA$*$, the variant of FedDCA, utilizes heterogeneous encoders with server-side feature alignment.
  arXiv  Detail & Related papers  (2024-09-30T09:34:31Z)
• P4: Towards private, personalized, and Peer-to-Peer learning [6.693404985718457]
  Two main challenges of personalization are client clustering and data privacy. We develop P4 (Personalized Private Peer-to-Peer) a method that ensures that each client receives a personalized model. P4 outperforms the state-of-the-art of differential private P2P by up to 40 percent in terms of accuracy.
  arXiv  Detail & Related papers  (2024-05-27T23:04:37Z)
• Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning [3.9166000694570076]
  Decentralized learning (DL) offers a novel paradigm in machine learning by distributing training across clients without central aggregation. DL's peer-to-peer model raises challenges in protecting against inference attacks and privacy leaks. This work proposes three secret sharing-based dropout resilience approaches for privacy-preserving DL.
  arXiv  Detail & Related papers  (2024-04-27T19:17:02Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models [40.83058938096914]
  FedLMG is a one-shot Federated learning method with Local Model-Guided diffusion models.<n>Clients do not need access to any foundation models but only train and upload their local models.
  arXiv  Detail & Related papers  (2023-11-15T11:11:25Z)
• P4L: Privacy Preserving Peer-to-Peer Learning for Infrastructureless Setups [5.601217969637838]
  P4L is a privacy preserving peer-to-peer learning system for users to participate in an asynchronous, collaborative learning scheme. Our design uses strong cryptographic primitives to preserve both the confidentiality and utility of the shared gradients.
  arXiv  Detail & Related papers  (2023-02-26T23:30:18Z)
• Straggler-Resilient Personalized Federated Learning [55.54344312542944]
  Federated learning allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions. We develop a novel algorithmic procedure with theoretical speedup guarantees that simultaneously handles two of these hurdles. Our method relies on ideas from representation learning theory to find a global common representation using all clients' data and learn a user-specific set of parameters leading to a personalized solution for each client.
  arXiv  Detail & Related papers  (2022-06-05T01:14:46Z)
• PerFED-GAN: Personalized Federated Learning via Generative Adversarial Networks [46.17495529441229]
  Federated learning is a distributed machine learning method that can be used to deploy AI-dependent IoT applications. This paper proposes a federated learning method based on co-training and generative adversarial networks(GANs) In our experiments, the proposed method outperforms the existing methods in mean test accuracy by 42% when the client's model architecture and data distribution vary significantly.
  arXiv  Detail & Related papers  (2022-02-18T12:08:46Z)
• Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design [76.29738151117583]
  Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, low quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. We model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk.
  arXiv  Detail & Related papers  (2021-05-10T08:02:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.