Practical One-Shot Federated Learning for Cross-Silo Setting
This addresses the practical need for efficient and private federated learning in cross-silo environments, offering a novel solution to reduce communication rounds while maintaining flexibility and privacy.
The paper tackles the problem of one-shot federated learning in cross-silo settings by proposing FedKT, which uses knowledge transfer to support any classification models and provide differential privacy, achieving significant performance improvements over state-of-the-art algorithms in a single communication round.
Federated learning enables multiple parties to collaboratively learn a model without exchanging their data. While most existing federated learning algorithms need many rounds to converge, one-shot federated learning (i.e., federated learning with a single communication round) is a promising approach to make federated learning applicable in cross-silo setting in practice. However, existing one-shot algorithms only support specific models and do not provide any privacy guarantees, which significantly limit the applications in practice. In this paper, we propose a practical one-shot federated learning algorithm named FedKT. By utilizing the knowledge transfer technique, FedKT can be applied to any classification models and can flexibly achieve differential privacy guarantees. Our experiments on various tasks show that FedKT can significantly outperform the other state-of-the-art federated learning algorithms with a single communication round.