Data-free knowledge distillation-based one-shot federated learning (OSFL) trains a model in a single communication round without sharing raw data, making OSFL attractive for privacy-sensitive medical applications. However, existing methods aggregate predictions from all clients to form a global teacher. Under non-IID data, conflicting predictions dilute each other during averaging, yielding less informative soft labels that weaken distillation. We propose FedBiCross, a personalized OSFL framework with three stages: (1) clustering clients by model output similarity to form coherent sub-ensembles, (2) bi-level cross-cluster optimization that learns adaptive weights to selectively leverage beneficial cross-cluster knowledge while suppressing negative transfer, and (3) personalized distillation for client-specific adaptation. Experiments on four medical image datasets demonstrate that FedBiCross consistently outperforms state-of-the-art baselines across different non-IID degrees.

翻译：基于无数据知识蒸馏的单次联邦学习（OSFL）在单轮通信中完成模型训练且无需共享原始数据，这使得OSFL对隐私敏感的医疗应用具有吸引力。然而，现有方法整合所有客户端的预测结果以形成全局教师模型。在非独立同分布数据场景下，相互矛盾的预测在平均过程中相互稀释，从而生成信息量较低的软标签并削弱蒸馏效果。我们提出FedBiCross框架，这是一个包含三阶段流程的个性化OSFL方法：(1) 根据模型输出相似性对客户端聚类以形成连贯子集成；(2) 双层跨集群优化机制，通过自适应权重学习有选择地利用有益的跨集群知识并抑制负迁移；(3) 针对客户端特定适配的个性化蒸馏。在四个医学图像数据集上的实验表明，FedBiCross在不同非独立同分布程度下均持续优于现有最优基线方法。