# FedPDC:Federated Learning for Public Dataset Correction

## TL;DR

FedPDC introduces a novel federated learning algorithm that improves global model accuracy in highly unbalanced data scenarios by optimizing local model aggregation and loss functions, all while preserving client privacy and maintaining communication efficiency.

## Contribution

The paper proposes FedPDC, a new federated learning method that enhances model accuracy in Non-IID data environments through shared industry datasets and optimized aggregation.

## Key findings

- Significant accuracy improvements in unbalanced data scenarios.
- Maintains privacy of client data during training.
- No additional communication costs introduced.

## Abstract

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.