FedPDC:Federated Learning for Public Dataset Correction
This work addresses accuracy issues in federated learning for privacy-sensitive applications, but it appears incremental as it builds on existing optimization methods.
The paper tackles the problem of lower classification accuracy in federated learning under Non-IID data distributions by proposing FedPDC, which optimizes local model aggregation and loss functions using shared datasets, resulting in improved global model accuracy without additional communication costs in benchmark experiments.
As people pay more and more attention to privacy protection, Federated Learning (FL), as a promising distributed machine learning paradigm, is receiving more and more attention. However, due to the biased distribution of data on devices in real life, federated learning has lower classification accuracy than traditional machine learning in Non-IID scenarios. Although there are many optimization algorithms, the local model aggregation in the parameter server is still relatively traditional. In this paper, a new algorithm FedPDC is proposed to optimize the aggregation mode of local models and the loss function of local training by using the shared data sets in some industries. In many benchmark experiments, FedPDC can effectively improve the accuracy of the global model in the case of extremely unbalanced data distribution, while ensuring the privacy of the client data. At the same time, the accuracy improvement of FedPDC does not bring additional communication costs.