pFedAFM: Adaptive Feature Mixture for Data-Level Personalization in Heterogeneous Federated Learning on Mobile Edge Devices

作者：Liping Yi, Han Yu, Gang Wang, Xiaoguang Liu, Xiaoxiao Li · 年份：2025 · DOI：10.1109/icde65448.2025.00151 · 被引用次数：4 · 研究领域：Privacy-Preserving Technologies in Data、Caching and Content Delivery、Recommender Systems and Techniques

Federated learning (FL), an emerging distributed machine learning paradigm, utilizes edge decentralized data from multiple edge nodes (clients) to train a shared model under preserved data privacy. Furthermore, model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (non-lID) local data. Existing MHPFL methods focus on data distribution differences among clients, and they propose various client-level personalization approaches to alleviate non-lID issues. However, different data samples in one client may also have different features, which are often ignored, resulting in constrained model performances. To bridge this gap, we propose a novel model-heterogeneous personalized Federated learning approach with Adaptive Feature Mixture (pFedAFM) to achieve data-level personalization while maintaining efficient communication and computation. It consists of three innovative designs: 1) We add a homogeneous small feature extractor alongside each client's local heterogeneous model, and the server aggregates these homogeneous small feature extractors for cross-client knowledge fusion. 2) We design an iterative training strategy to alternately train the global homogeneous small feature extractor and the local heterogeneous client model, for effective bidirectional exchange between global generalized knowledge and local personalized knowledge. 3) During model training,...