标题： pFedDSH：通过无数据子超网络在个性化联邦学习中实现知识迁移 显示英文标题

标题： pFedDSH: Enabling Knowledge Transfer in Personalized Federated Learning through Data-free Sub-Hypernetwork

摘要： 联邦学习（FL）允许在不共享原始数据的情况下在分布式客户端之间进行协作模型训练，提供了显著的隐私优势。 然而，大多数现有的个性化联邦学习（pFL）方法假设客户端参与是静态的，这并不反映现实场景，其中新客户端可能会持续加入联邦系统（即动态客户端接入）。 在本文中，我们探讨了一个实际场景，在该场景中，新的客户端批次被逐步引入，而学习任务保持不变。 这种动态环境带来了各种挑战，包括在不重新训练的情况下保持现有客户端的性能，并在客户端批次之间实现高效的知识迁移。 为了解决这些问题，我们提出了个性化联邦无数据子超网络（pFedDSH），这是一种基于中心超网络的新框架，通过嵌入向量为每个客户端生成个性化模型。 为了保持现有客户端的知识稳定性，pFedDSH结合了批次特定的掩码，这些掩码激活神经元子集以保留知识。 此外，我们引入了一种受DeepInversion启发的无数据重放策略，以促进后向迁移，提高现有客户端的性能而不损害隐私。 在CIFAR-10、CIFAR-100和Tiny-ImageNet上进行的大量实验表明，pFedDSH在我们的研究场景中优于最先进的pFL和联邦持续学习基线。 我们的方法在现有客户端上实现了稳健的性能稳定性，同时实现了新客户端的适应性和神经资源的高效利用。 显示英文摘要

摘要： Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, offering a significant privacy benefit. However, most existing Personalized Federated Learning (pFL) methods assume a static client participation, which does not reflect real-world scenarios where new clients may continuously join the federated system (i.e., dynamic client onboarding). In this paper, we explore a practical scenario in which a new batch of clients is introduced incrementally while the learning task remains unchanged. This dynamic environment poses various challenges, including preserving performance for existing clients without retraining and enabling efficient knowledge transfer between client batches. To address these issues, we propose Personalized Federated Data-Free Sub-Hypernetwork (pFedDSH), a novel framework based on a central hypernetwork that generates personalized models for each client via embedding vectors. To maintain knowledge stability for existing clients, pFedDSH incorporates batch-specific masks, which activate subsets of neurons to preserve knowledge. Furthermore, we introduce a data-free replay strategy motivated by DeepInversion to facilitate backward transfer, enhancing existing clients' performance without compromising privacy. Extensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that pFedDSH outperforms the state-of-the-art pFL and Federated Continual Learning baselines in our investigation scenario. Our approach achieves robust performance stability for existing clients, as well as adaptation for new clients and efficient utilization of neural resources.