Personalized Federated Learning via Heterogeneous Modular Networks
This addresses the challenge of personalizing federated models for diverse clients under privacy constraints, representing an incremental improvement over existing PFL methods.
The paper tackles the problem of sub-optimal solutions in Personalized Federated Learning (PFL) when client data distributions diverge, by proposing Federated Modular Network (FedMN), which adaptively assembles heterogeneous neural architectures for different clients, showing effectiveness and efficiency in experiments.
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 the effectiveness and efficiency of the proposed FedMN over the baselines.