Provably Near-Optimal Federated Ensemble Distillation with Negligible Overhead
This work addresses client heterogeneity in federated learning, offering an incremental improvement with practical benefits for privacy-preserving distributed AI systems.
The paper tackles client heterogeneity in federated ensemble distillation by proposing a provably near-optimal weighting method for pseudo-label generation, which significantly outperforms baselines in image classification tasks with negligible overhead in communication, privacy, and computation.
Federated ensemble distillation addresses client heterogeneity by generating pseudo-labels for an unlabeled server dataset based on client predictions and training the server model using the pseudo-labeled dataset. The unlabeled server dataset can either be pre-existing or generated through a data-free approach. The effectiveness of this approach critically depends on the method of assigning weights to client predictions when creating pseudo-labels, especially in highly heterogeneous settings. Inspired by theoretical results from GANs, we propose a provably near-optimal weighting method that leverages client discriminators trained with a server-distributed generator and local datasets. Our experiments on various image classification tasks demonstrate that the proposed method significantly outperforms baselines. Furthermore, we show that the additional communication cost, client-side privacy leakage, and client-side computational overhead introduced by our method are negligible, both in scenarios with and without a pre-existing server dataset.