Personalized Models refer to customized or individualized versions of algorithms, machine learning models, or systems that are tailored to specific users’ preferences, behaviors, or characteristics. These models are designed to provide personalized experiences, recommendations, or predictions by adapting to the unique needs and patterns of each user, often based on their historical interactions, feedback, and data. Personalized models are commonly employed in applications such as personalized content recommendations, targeted advertising, and user-specific predictions to enhance user satisfaction and engagement.


Personalized Federated Learning via Heterogeneous Modular Networks

Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite its popularity, it has been observed that existing PFL approaches result in sub-optimal solutions when the joint distribution among local clients diverges. To address this issue, we present Federated Modular Network (FedMN), a novel PFL approach that adaptively selects sub-modules from a module pool to assemble heterogeneous neural architectures for different clients. FedMN adopts a light-weighted routing hypernetwork to model the joint distribution on each client and produce the personalized selection of the module blocks for each client. To reduce the communication burden in existing FL, we develop an efficient way to interact between the clients and the server. We conduct extensive experiments on the real-world test beds and the results show both effectiveness and efficiency of the proposed FedMN over the baselines.