pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning

• URL: http://arxiv.org/abs/2606.16304v1
• Date: Mon, 15 Jun 2026 07:07:55 GMT
• Title: pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning
• Abstract summary: Federated unlearning (FU) enables removal of specific contributions from federated learning (FL) models.<n>Most existing methods are designed for the FedAvg paradigm, where all clients share a single global model.<n>We formalize FU under the pFL paradigm, identifying a tension between unlearning preservation on shared layers and personalization for remaining clients.
• Score: 3.8750005648250316
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated unlearning (FU) enables the removal of specific data contributions from federated learning (FL) models to comply with regulations such as the General Data Protection Regulation (GDPR). However, most existing FU methods are designed for the FedAvg paradigm, where all clients share a single global model. In practice, personalized federated learning (pFL) methods such as FedPer, FedRep, Ditto, and FedBN have become widely adopted due to their superior handling of non-IID data. These methods decompose the model into shared global layers and client-specific personalized layers, fundamentally altering the semantics of unlearning, yet this setting has received little attention. We formalize FU under the pFL paradigm, identifying a tension between unlearning completeness on shared layers and personalization preservation for remaining clients. We then propose pFedUL, a layer-aware selective unlearning framework comprising three components: (1) gradient-based layer-wise contribution attribution that separately quantifies the target client's influence on shared and personalized parameters, (2) adaptive selective unlearning that applies differentiated forgetting strategies across layer types, and (3) a lightweight recalibration protocol enabling remaining clients to restore personalization with minimal overhead. We further introduce two new metrics, Personalization Preservation Score (PPS) and Cross-client Fairness Index (CFI), to evaluate pFL-specific unlearning quality. Experiments on CIFAR-10, CIFAR-100, and FEMNIST under varying non-IID settings indicate that pFedUL achieves unlearning effectiveness comparable to full retraining while maintaining an average of 97.3\% personalized accuracy for remaining clients. Compared with six state-of-the-art FU methods adapted to the pFL setting, pFedUL consistently achieves superior personalization preservation.

Related papers

• Separate Aggregation of Split Network for Personalized Federated Learning [0.9668407688201359]
  Federated learning can degrade substantially under heterogeneous client data distributions.<n>We propose PGFedSplit, a personalized federated learning framework.<n>Experiments on Fashion MNIST, CIFAR 10, CIFAR 100, and Tiny ImageNet demonstrate consistent improvements over state of the art PFL methods.
  arXiv  Detail & Related papers  (2026-05-26T05:44:30Z)
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• 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)
• FedPPA: Progressive Parameter Alignment for Personalized Federated Learning [0.9931624906346306]
  Federated Learning (FL) is designed as a decentralized, privacy-preserving machine learning paradigm that enables multiple clients to collaboratively train a model without sharing their data.<n>In real-world scenarios, clients often have heterogeneous computational resources and hold non-independent and identically distributed data (non-IID), which poses significant challenges during training.<n>We propose Progressive Alignment (FedPPA), which progressively aligns the weights of common layers across clients with the global model's weights.<n>Experiments on three image classification datasets, including MNIST, FMNIST, and CIFAR-10, demonstrate that FedPPA consistently outperforms existing FL algorithms,
  arXiv  Detail & Related papers  (2025-10-16T14:03:05Z)
• Whom to Trust? Adaptive Collaboration in Personalized Federated Learning [11.923664505655026]
  We show that adaptivity in collaboration and fine-grained trust, at the level of individual examples, can be achieved within federated semi-supervised learning.<n>We develop FEDMOSAIC, a personalized co-training method where clients reweight their loss and their contribution to pseudo-labels based on per-example agreement and confidence.
  arXiv  Detail & Related papers  (2025-06-30T20:53:01Z)
• FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Data [5.906966694759679]
  FedAPA is a novel PFL method featuring a server-side, gradient-based adaptive aggregation strategy to generate personalized models.<n>FedAPA guarantees theoretical convergence and achieves superior accuracy and computational efficiency compared to 10 PFL competitors across three datasets.
  arXiv  Detail & Related papers  (2025-02-11T11:00:58Z)
• UA-PDFL: A Personalized Approach for Decentralized Federated Learning [5.065947993017158]
  Federated learning (FL) is a privacy preserving machine learning paradigm designed to collaboratively learn a global model without data leakage.<n>To mitigate this issue, decentralized federated learning (DFL) has been proposed, where all participating clients engage in peer-to-peer communication without a central server.<n>We propose a novel unit representation aided personalized decentralized federated learning framework, named UA-PDFL, to deal with the non-IID challenge in DFL.
  arXiv  Detail & Related papers  (2024-12-16T11:27:35Z)
• PPFL: A Personalized Federated Learning Framework for Heterogeneous Population [27.93326556470552]
  Personalization aims to characterize individual preferences and is widely applied across many fields.<n>Conventional personalized methods operate in a centralized manner, potentially exposing raw data when pooling individual information.<n>We develop a flexible and interpretable personalized framework within the paradigm of a Population Personalized Federated Learning.
  arXiv  Detail & Related papers  (2023-10-22T16:06:27Z)
• Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings [41.98633628526484]
  Mixture-of-Experts (MoEs) achieve scalability by dynamically activating subsets of their components.<n>Motivated by inference costs and data heterogeneity, we study how joint training of gating functions and experts can allocate domain-specific expertise.
  arXiv  Detail & Related papers  (2023-06-14T15:47:52Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation [24.679535905451758]
  PFL aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods assume that the underlying global data across all clients are uniformly distributed without considering the long-tail distribution. We propose Federated Learning with Adversarial Feature Augmentation (FedAFA) to address this joint problem in PFL.
  arXiv  Detail & Related papers  (2023-03-27T13:00:20Z)
• Subspace based Federated Unlearning [75.90552823500633]
  Federated unlearning (FL) aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates. We propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, that lets the global model perform gradient ascent.
  arXiv  Detail & Related papers  (2023-02-24T04:29:44Z)
• FedABC: Targeting Fair Competition in Personalized Federated Learning [76.9646903596757]
  Federated learning aims to collaboratively train models without accessing their client's local private data. We propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the one-vs-all'' training strategy in each client to alleviate the unfair competition between classes.
  arXiv  Detail & Related papers  (2023-02-15T03:42:59Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)

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.