Heterogeneous Federated Learning (HtFL) enables collaborative learning on multiple clients with different model architectures while preserving privacy. Despite recent research progress, knowledge sharing in HtFL is still difficult due to data and model heterogeneity. To tackle this issue, we leverage the knowledge stored in pre-trained generators and propose a new upload-efficient knowledge transfer scheme called Federated Knowledge-Transfer Loop (FedKTL). Our FedKTL can produce client-task-related prototypical image-vector pairs via the generator's inference on the server. With these pairs, each client can transfer pre-existing knowledge from the generator to its local model through an additional supervised local task. We conduct extensive experiments on four datasets under two types of data heterogeneity with 14 kinds of models including CNNs and ViTs. Results show that our upload-efficient FedKTL surpasses seven state-of-the-art methods by up to 7.31% in accuracy. Moreover, our knowledge transfer scheme is applicable in scenarios with only one edge client. Code: https://github.com/TsingZ0/FedKTL

翻译：异构联邦学习（HtFL）能够在保护隐私的前提下，支持具有不同模型架构的多个客户端进行协同学习。尽管近期研究取得进展，但由于数据和模型的异构性，HtFL中的知识共享仍面临挑战。为解决该问题，我们利用预训练生成器中存储的知识，提出了一种名为联邦知识传输循环（FedKTL）的新型高效上传知识传输方案。我们的FedKTL可通过服务器端生成器的推理，产生与客户端任务相关的原型图像-向量对。借助这些配对，每个客户端能够通过额外的监督式本地任务，将生成器中的既有知识迁移至其本地模型。我们在四种数据集、两种数据异构类型下，使用包含CNN和ViT在内的14种模型进行了广泛实验。结果表明，我们提出的高效上传FedKTL方法在准确率上最高超越七种当前最优方法达7.31%。此外，我们的知识传输方案同样适用于仅含单个边缘客户端的场景。代码地址：https://github.com/TsingZ0/FedKTL