HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer

• URL: http://arxiv.org/abs/2603.24209v1
• Date: Wed, 25 Mar 2026 11:35:07 GMT
• Title: HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer
• Abstract summary: HEART-PFL is a dual-sided framework that performs depth-aware Hierarchical Directional Alignment.<n>It stabilizes global updates through Adversarial Knowledge Transfer (AKT) with symmetric KL distillation on clean and adversarial proxy data.<n>Using lightweight adapters with only 1.46M trainable parameters, HEART-PFL achieves state-of-the-art personalized accuracy.
• Score: 28.18683870049843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personalized Federated Learning (PFL) aims to deliver effective client-specific models under heterogeneous distributions, yet existing methods suffer from shallow prototype alignment and brittle server-side distillation. We propose HEART-PFL, a dual-sided framework that (i) performs depth-aware Hierarchical Directional Alignment (HDA) using cosine similarity in the early stage and MSE matching in the deep stage to preserve client specificity, and (ii) stabilizes global updates through Adversarial Knowledge Transfer (AKT) with symmetric KL distillation on clean and adversarial proxy data. Using lightweight adapters with only 1.46M trainable parameters, HEART-PFL achieves state-of-the-art personalized accuracy on CIFAR-100, Flowers-102, and Caltech-101 (63.42%, 84.23%, and 95.67%, respectively) under Dirichlet non-IID partitions, and remains robust to out-of-domain proxy data. Ablation studies further confirm that HDA and AKT provide complementary gains in alignment, robustness, and optimization stability, offering insights into how the two components mutually reinforce effective personalization. Overall, these results demonstrate that HEART-PFL simultaneously enhances personalization and global stability, highlighting its potential as a strong and scalable solution for PFL(code available at https://github.com/danny0628/HEART-PFL).

Related papers

• 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)
• 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)
• OvA-LP: A Simple and Efficient Framework for Federated Learning on Non-IID Data [3.2207230906189945]
  OvA-LP is designed to suppress drift at its source within the PEFT-based FFT paradigm.<n>On CIFAR-100 with 100 clients, OvA-LP retains 95.9% of its IID accuracy, whereas state-of-the-art FFT baselines retain only 10.1% (PFPT) and 34.5% (FFT-MoE) under the same conditions.
  arXiv  Detail & Related papers  (2025-11-07T07:00:20Z)
• 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)
• On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairness [16.595935469099306]
  We propose FLAME, an optimization framework by utilizing the alternating direction method of multipliers (ADMM) to train personalized and global models. Our theoretical analysis establishes the global convergence and two kinds of convergence rates for FLAME under mild assumptions. Our experimental findings show that FLAME outperforms state-of-the-art methods in convergence and accuracy, and it achieves higher test accuracy under various attacks.
  arXiv  Detail & Related papers  (2024-07-23T11:35:42Z)
• Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning [49.72857433721424]
  Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. We present a novel algorithm, SGPT, that integrates Generalized FL (GFL) and Personalized FL (PFL) approaches by employing a unique combination of both shared and group-specific prompts.
  arXiv  Detail & Related papers  (2023-10-27T17:22:09Z)
• PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees [95.87604231887353]
  Existing pFL methods introduce high communication and computation costs or are vulnerable to test communication. In PerAda, a parameter distillation and pFL pFL has superior performance, especially under test-time distribution. Our code is available at https://github.com/NV/PerAda.
  arXiv  Detail & Related papers  (2023-02-13T19:00:37Z)
• Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models [36.84027517814128]
  Federated learning (FL) trains massive and geographically distributed edge data while maintaining privacy. We propose a Customized Federated Learning (CFL) system to eliminate FL heterogeneity from multiple dimensions. CFL tailors personalized models from the specially designed global model for each client jointly guided by an online trained model-search helper and a novel aggregation algorithm.
  arXiv  Detail & Related papers  (2023-02-09T06:55:19Z)
• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning [66.56240101249803]
  We study how hardening benign clients can affect the global model (and the malicious clients) We propose a trigger reverse engineering based defense and show that our method can achieve improvement with guarantee robustness. Our results on eight competing SOTA defense methods show the empirical superiority of our method on both single-shot and continuous FL backdoor attacks.
  arXiv  Detail & Related papers  (2022-10-23T22:24:03Z)
• 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.