Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

• URL: http://arxiv.org/abs/2604.20596v1
• Date: Wed, 22 Apr 2026 14:12:18 GMT
• Title: Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
• Abstract summary: Federated learning (FL) enables training of a global model while keeping raw data on end-devices.<n>Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as differential privacy (DP) and secure vector sum to provide formal privacy guarantees to its participants.<n>We propose PINA, a two-stage framework that lets each client fine-tune a lightweight low-rank adaptation (LoRA) adapter and privately share a compressed sketch of the update.<n>In the second stage, PINA introduces a normality-driven aggregation mechanism that improves convergence and robustness.
• Score: 25.94292199187493
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as differential privacy (DP) and secure vector sum to provide formal privacy guarantees to its participants. In realistic cross-device deployments, the data are highly heterogeneous, so vanilla federated learning converges slowly and generalizes poorly. Clustered federated learning (CFL) mitigates this by segregating users into clusters, leading to lower intra-cluster data heterogeneity. Nevertheless, coupling CFL with DP remains challenging: the injected DP noise makes individual client updates excessively noisy, and the server is unable to initialize cluster centroids with the less noisy aggregated updates. To address this challenge, we propose PINA, a two-stage framework that first lets each client fine-tune a lightweight low-rank adaptation (LoRA) adapter and privately share a compressed sketch of the update. The server leverages these sketches to construct robust cluster centroids. In the second stage, PINA introduces a normality-driven aggregation mechanism that improves convergence and robustness. Our method retains the benefits of clustered FL while providing formal privacy guarantees against an untrusted server. Extensive evaluations show that our proposed method outperforms state-of-the-art DP-FL algorithms by an average of 2.9% in accuracy for privacy budgets (epsilon in {2, 8}).

Related papers

• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks [51.43780477302533]
  Contribution-Oriented PFL (CO-PFL) is a novel algorithm that dynamically estimates each client's contribution for global aggregation.<n>CO-PFL consistently surpasses state-of-the-art methods in robustness in personalization accuracy, robustness, scalability and convergence stability.
  arXiv  Detail & Related papers  (2025-10-23T05:10:06Z)
• Pigeon-SL: Robust Split Learning Framework for Edge Intelligence under Malicious Clients [53.496957000114875]
  We introduce Pigeon-SL, a novel scheme that guarantees at least one entirely honest cluster among M clients, even when up to N of them are adversarial.<n>In each global round, the access point partitions the clients into N+1 clusters, trains each cluster independently via vanilla SL, and evaluates their validation losses on a shared dataset.<n>Only the cluster with the lowest loss advances, thereby isolating and discarding malicious updates.
  arXiv  Detail & Related papers  (2025-08-04T09:34:50Z)
• DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing [51.336015600778396]
  We introduce the distributed matrix mechanism to achieve the best-of-both-worlds; better privacy of distributed DP and better utility from the matrix mechanism.<n>We accomplish this using a novel cryptographic protocol that securely transfers sensitive values across client committees of different training iterations with constant communication overhead.
  arXiv  Detail & Related papers  (2024-10-21T16:25:14Z)
• Differentially Private Clustered Federated Learning [4.768272342753616]
  Federated learning (FL) often incorporates differential privacy (DP) to provide rigorous data privacy guarantees.<n>Previous works attempted to address high structured data heterogeneity in vanilla FL settings through clustering clients (a.k.a clustered FL)<n>We propose an algorithm for differentially private clustered FL, which is robust to the DP noise in the system and identifies the underlying clients' clusters correctly.
  arXiv  Detail & Related papers  (2024-05-29T17:03:31Z)
• DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation [15.023077875990614]
  Federated learning (FL) allows clients to collaboratively train a global model without sharing their local data with a server.<n> Differential privacy (DP) addresses such leakage by providing formal privacy guarantees, with mechanisms that add randomness to the clients' contributions.<n>We propose an adaptation method that can be combined with differential privacy and call it DP-DyLoRA.
  arXiv  Detail & Related papers  (2024-05-10T10:10:37Z)
• Compressed Private Aggregation for Scalable and Robust Federated Learning over Massive Networks [34.29747990203208]
  Federated learning (FL) is an emerging paradigm that allows a central server to train machine learning models using remote users' data.<n>FL faces challenges in preserving the privacy of local datasets, its sensitivity to poisoning attacks by malicious users, and its communication overhead.<n>We present compressed private aggregation (CPA), that allows massive deployments to simultaneously communicate at extremely low bit rates.
  arXiv  Detail & Related papers  (2023-08-01T13:36:33Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Differentially Private Federated Clustering over Non-IID Data [59.611244450530315]
  clustering clusters (FedC) problem aims to accurately partition unlabeled data samples distributed over massive clients into finite clients under the orchestration of a server. We propose a novel FedC algorithm using differential privacy convergence technique, referred to as DP-Fed, in which partial participation and multiple clients are also considered. Various attributes of the proposed DP-Fed are obtained through theoretical analyses of privacy protection, especially for the case of non-identically and independently distributed (non-i.i.d.) data.
  arXiv  Detail & Related papers  (2023-01-03T05:38:43Z)
• Social-Aware Clustered Federated Learning with Customized Privacy Preservation [38.00035804720786]
  We propose a novel Social-aware Clustered Federated Learning scheme, where mutually trusted individuals can freely form a social cluster. By mixing model updates in a social group, adversaries can only eavesdrop the social-layer combined results, but not the privacy of individuals. Experiments on Facebook network and MNIST/CIFAR-10 datasets validate that our SCFL can effectively enhance learning utility, improve user payoff, and enforce customizable privacy protection.
  arXiv  Detail & Related papers  (2022-12-25T10:16:36Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Stochastic Coded Federated Learning with Convergence and Privacy Guarantees [8.2189389638822]
  Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework. This paper proposes a coded federated learning framework, namely coded federated learning (SCFL) to mitigate the straggler issue. We characterize the privacy guarantee by the mutual information differential privacy (MI-DP) and analyze the convergence performance in federated learning.
  arXiv  Detail & Related papers  (2022-01-25T04:43:29Z)
• FedMix: Approximation of Mixup under Mean Augmented Federated Learning [60.503258658382]
  Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device. Current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. We propose a new augmentation algorithm, named FedMix, which is inspired by a phenomenal yet simple data augmentation method, Mixup.
  arXiv  Detail & Related papers  (2021-07-01T06:14:51Z)

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.