Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data sources. To protect data privacy and unify data silos among end devices in EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across devices without compromising data privacy. However, the prevailing FL approaches cannot guarantee model generalization and adaptation on heterogeneous clients. Recently, Personalized Federated Learning (PFL) has drawn growing awareness in EI, as it enables a productive balance between local-specific training requirements inherent in devices and global-generalized optimization objectives for satisfactory performance. However, most existing PFL methods are based on the Parameters Interaction-based Architecture (PIA) represented by FedAvg, which causes unaffordable communication burdens due to large-scale parameters transmission between devices and the edge server. In contrast, Logits Interaction-based Architecture (LIA) allows to update model parameters with logits transfer and gains the advantages of communication lightweight and heterogeneous on-device model allowance compared to PIA. Nevertheless, previous LIA methods attempt to achieve satisfactory performance either relying on unrealistic public datasets or increasing communication overhead for additional information transmission other than logits. To tackle this dilemma, we propose a knowledge cache-driven PFL architecture, named FedCache, which reserves a knowledge cache on the server for fetching personalized knowledge from the samples with similar hashes to each given on-device sample. During the training phase, ensemble distillation is applied to on-device models for constructive optimization with personalized knowledge transferred from the server-side knowledge cache.

翻译：边缘智能（EI）允许人工智能应用在边缘端运行，实现实时数据分析和决策并靠近数据源。为保护数据隐私并统一EI终端设备间的数据孤岛，联邦学习（FL）被提出用于跨设备协作训练共享AI模型，同时不损害数据隐私。然而，现有主流FL方法无法保证模型在异构客户端上的泛化性和适应性。近年来，个性化联邦学习（PFL）在EI领域日益受到关注，因为它能在设备固有的本地特定训练需求与全局泛化优化目标之间实现有效平衡，从而获得令人满意的性能。但现有大多数PFL方法基于以FedAvg为代表的参数交互架构（PIA），由于设备与边缘服务器之间的大规模参数传输，导致难以承受的通信负担。相比之下，基于逻辑交互架构（LIA）可通过逻辑值传输更新模型参数，与PIA相比具有通信轻量化和异构设备模型兼容等优势。然而，现有LIA方法若要取得满意性能，要么依赖不切实际的公共数据集，要么通过增加逻辑值之外的额外信息传输导致通信开销上升。为解决这一困境，我们提出一种知识缓存驱动的PFL架构FedCache，该架构在服务器端维护知识缓存，通过从具有相似哈希值的样本中为每个给定设备样本获取个性化知识。在训练阶段，采用集成蒸馏技术利用服务端知识缓存传输的个性化知识，对设备端模型进行构建性优化。