A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning

• URL: http://arxiv.org/abs/2511.12695v1
• Date: Sun, 16 Nov 2025 17:19:23 GMT
• Title: A Closer Look at Personalized Fine-Tuning in Heterogeneous Federated Learning
• Abstract summary: Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization.<n>We propose adapting Linear Probing followed by full Fine-Tuning (LP-FT), a principled centralized strategy for alleviating feature distortion.
• Score: 42.09768870974917
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning (PFT), a popular post-hoc solution, fine-tunes the final global model locally but often overfits to skewed client distributions or fails under domain shifts. We propose adapting Linear Probing followed by full Fine-Tuning (LP-FT), a principled centralized strategy for alleviating feature distortion (Kumar et al., 2022), to the FL setting. Through systematic evaluation across seven datasets and six PFT variants, we demonstrate LP-FT's superiority in balancing personalization and generalization. Our analysis uncovers federated feature distortion, a phenomenon where local fine-tuning destabilizes globally learned features, and theoretically characterizes how LP-FT mitigates this via phased parameter updates. We further establish conditions (e.g., partial feature overlap, covariate-concept shift) under which LP-FT outperforms standard fine-tuning, offering actionable guidelines for deploying robust personalization in FL.

Related papers

• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• 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)
• FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation [12.544628972135905]
  We introduce Federated Representation Fine-Tuning (FedReFT), a novel approach to fine-tune the client's hidden representation.<n>FedReFT applies sparse intervention layers to steer hidden representations directly, offering a lightweight and semantically rich fine-tuning alternative.<n>We evaluate FedReFT on commonsense reasoning, arithmetic reasoning, instruction-tuning, and GLUE.
  arXiv  Detail & Related papers  (2025-08-27T22:03:19Z)
• Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation [12.19025665853089]
  In traditional Federated Learning approaches, the global model underperforms when faced with data heterogeneity. We propose a new PFL framework called FedPFT to address the mismatch problem while enhancing the quality of the feature extractor. Our experiments demonstrate that FedPFT outperforms state-of-the-art methods by up to 7.08%.
  arXiv  Detail & Related papers  (2024-07-23T02:52:52Z)
• 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)
• 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)
• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [104.19414150171472]
  Attributes skews the current federated learning (FL) frameworks from consistent optimization directions among the clients. We propose disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches. Experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods.
  arXiv  Detail & Related papers  (2022-06-14T13:12:12Z)

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.