Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

• URL: http://arxiv.org/abs/2605.02247v1
• Date: Mon, 04 May 2026 05:41:10 GMT
• Title: Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning
• Abstract summary: We propose Federated Learning via Gradient Purification and Residual Learning (FedPuReL)<n>FedPuReL preserves balanced knowledge in the global model while enabling unbiased personalization.<n>Experiments demonstrate that FedPuReL consistently outperforms state-of-the-art methods.
• Score: 14.554714155285374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personalized federated learning (PFL) with foundation models has emerged as a promising paradigm enabling clients to adapt to heterogeneous data distributions. However, real-world scenarios often face the co-occurrence of non-IID data and long-tailed class distributions, presenting unique challenges that remain underexplored in PFL. In this paper, we investigate this long-tailed personalized federated learning and observe that current methods suffer from two limitations: (i) fine-tuning degrades performance below zero-shot baselines due to the erosion of inherent class balance in foundation models; (ii) conventional personalization techniques further transfer this bias to local models through parameter or feature-level fusion. To address these challenges, we propose Federated Learning via Gradient Purification and Residual Learning (FedPuReL), which preserves balanced knowledge in the global model while enabling unbiased personalization. Specifically, we purify local gradients using zero-shot predictions to maintain a class-balanced global model, and model personalization as residual correction atop the frozen global model. Extensive experiments demonstrate that FedPuReL consistently outperforms state-of-the-art methods, achieving superior performance on both global and personalized models across diverse long-tailed scenarios. The code is available at https://github.com/shihaohou/FedPuReL.

Related papers

• FedImpro: Measuring and Improving Client Update in Federated Learning [77.68805026788836]
  Federated Learning (FL) models often experience client drift caused by heterogeneous data. We present an alternative perspective on client drift and aim to mitigate it by generating improved local models.
  arXiv  Detail & Related papers  (2024-02-10T18:14:57Z)
• FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data [46.29190753993415]
  Federated Long-Tailed Learning (Fed-LT) is a paradigm wherein data collected from decentralized local clients manifests a globally prevalent long-tailed distribution. This paper introduces an approach termed Federated Local and Generic Model Training in Fed-LT (FedLoGe), which enhances both local and generic model performance.
  arXiv  Detail & Related papers  (2024-01-17T05:04:33Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning [16.344719695572586]
  We propose a novel scheme to inject personalized prior knowledge into a global model in each client. At the heart of our proposed approach is a framework, the PFL with Bregman Divergence (pFedBreD) Our method reaches the state-of-the-art performances on 5 datasets and outperforms other methods by up to 3.5% across 8 benchmarks.
  arXiv  Detail & Related papers  (2023-10-13T15:21:25Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training [67.67045085186797]
  Almost all existing systems have to face large communication burdens if the central FL server fails. It personalizes the "right" in the deep models by alternately updating the shared and personal parameters. To further promote the shared parameters aggregation process, we propose DFed integrating the local Sharpness Miniization.
  arXiv  Detail & Related papers  (2023-05-24T13:52:18Z)
• Confidence-aware Personalized Federated Learning via Variational Expectation Maximization [34.354154518009956]
  We present a novel framework for personalized Federated Learning (PFL) PFL is a distributed learning scheme to train a shared model across clients. We present a novel framework for PFL based on hierarchical modeling and variational inference.
  arXiv  Detail & Related papers  (2023-05-21T20:12:27Z)
• Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning [60.41501515192088]
  Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively. The data samples usually follow a long-tailed distribution in the real world, and FL on the decentralized and long-tailed data yields a poorly-behaved global model. In this work, we integrate the local real data with the global gradient prototypes to form the local balanced datasets.
  arXiv  Detail & Related papers  (2023-01-25T03:18:10Z)
• Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning [2.1044900734651626]
  We show how the chosen approach for training custom client models has an impact on the global model. We propose a new approach that combines KD and Learning without Forgetting (LwoF) to produce improved personalised models.
  arXiv  Detail & Related papers  (2022-11-07T11:12:57Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)

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.