Personalized Federated Learning via Stacking
This method addresses the need for tailored models in federated learning for clients with heterogeneous data, though it appears incremental as it builds on existing personalization techniques.
The paper tackles the problem of data heterogeneity in federated learning by proposing a personalized federated learning approach using stacked generalization, where clients exchange privacy-preserving models to train meta-models, resulting in improved performance across diverse simulated scenarios.
Traditional Federated Learning (FL) methods typically train a single global model collaboratively without exchanging raw data. In contrast, Personalized Federated Learning (PFL) techniques aim to create multiple models that are better tailored to individual clients' data. We present a novel personalization approach based on stacked generalization where clients directly send each other privacy-preserving models to be used as base models to train a meta-model on private data. Our approach is flexible, accommodating various privacy-preserving techniques and model types, and can be applied in horizontal, hybrid, and vertically partitioned federations. Additionally, it offers a natural mechanism for assessing each client's contribution to the federation. Through comprehensive evaluations across diverse simulated data heterogeneity scenarios, we showcase the effectiveness of our method.