FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
This addresses the problem of customizing models for clients with varied resources in federated learning, but it appears incremental as it adapts existing techniques.
The paper tackles the challenge of client-side model heterogeneity in federated learning by proposing FedP3, a framework for personalized and privacy-friendly network pruning, which theoretically validates its efficiency and includes a differentially private variant.
The interest in federated learning has surged in recent research due to its unique ability to train a global model using privacy-secured information held locally on each client. This paper pays particular attention to the issue of client-side model heterogeneity, a pervasive challenge in the practical implementation of FL that escalates its complexity. Assuming a scenario where each client possesses varied memory storage, processing capabilities and network bandwidth - a phenomenon referred to as system heterogeneity - there is a pressing need to customize a unique model for each client. In response to this, we present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning, tailored for model heterogeneity scenarios. Our proposed methodology can incorporate and adapt well-established techniques to its specific instances. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies.