A New One-Shot Federated Learning Framework for Medical Imaging Classification with Feature-Guided Rectified Flow and Knowledge Distillation

2025-07-25

AI Summary

To address the challenges of poor single-round convergence, inefficient generative training, and high privacy leakage risk in one-shot federated learning (OSFL) for multi-center medical image classification under non-IID data distributions, this paper proposes the FG-RF+DLKD framework. First, we design a Feature-Guided Rectified Flow (FG-RF) model that synthesizes feature-level—not pixel-level—images locally at clients, substantially reducing privacy risks and improving generation efficiency. Second, we introduce a Dual-Level Knowledge Distillation aggregation mechanism (DLKD) to achieve high-quality global model convergence within a single communication round. Experiments on three non-IID medical imaging datasets demonstrate that our method achieves an average performance gain of 21.75% over FedISCA, with a maximum improvement of 21.73%, while significantly enhancing privacy preservation.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Learning & Optimization for CV
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance

Abstract

In multi-center scenarios, One-Shot Federated Learning (OSFL) has attracted increasing attention due to its low communication overhead, requiring only a single round of transmission. However, existing generative model-based OSFL methods suffer from low training efficiency and potential privacy leakage in the healthcare domain. Additionally, achieving convergence within a single round of model aggregation is challenging under non-Independent and Identically Distributed (non-IID) data. To address these challenges, in this paper a modified OSFL framework is proposed, in which a new Feature-Guided Rectified Flow Model (FG-RF) and Dual-Layer Knowledge Distillation (DLKD) aggregation method are developed. FG-RF on the client side accelerates generative modeling in medical imaging scenarios while preserving privacy by synthesizing feature-level images rather than pixel-level images. To handle non-IID distributions, DLKD enables the global student model to simultaneously mimic the output logits and align the intermediate-layer features of client-side teacher models during aggregation. Experimental results on three non-IID medical imaging datasets show that our new framework and method outperform multi-round federated learning approaches, achieving up to 21.73% improvement, and exceeds the baseline FedISCA by an average of 21.75%. Furthermore, our experiments demonstrate that feature-level synthetic images significantly reduce privacy leakage risks compared to pixel-level synthetic images.

Problem

• Improving training efficiency in one-shot federated learning for medical imaging
• Addressing privacy leakage risks in healthcare data with feature-level synthesis
• Enhancing model convergence under non-IID data distributions in OSFL

Innovation

• Feature-Guided Rectified Flow Model for privacy
• Dual-Layer Knowledge Distillation for non-IID data
• Synthetic feature-level images reduce privacy risks