Can I read FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining on EtoBox?

FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining by Gain, Mrityunjoy; Kim, Kitae; Raha, Avi Deb; Adhikary, Apurba; Huh, Eui-Nam; Han, Zhu; Hong, Choong Seon is a scholarly article available to read on EtoBox.

What is FedFeat+: A Robust Federated Learning Framework Through Federated Aggregation and Differentially Private Feature-Based Classifier Retraining about?

In this paper, we propose the FedFeat+ framework, which distinctively separates feature extraction from classification. We develop a two-tiered model training process: following local training, clients transmit their weights and some features extracted from the feature extractor from the final local epochs to the server. The server aggregates these models using the FedAvg method and subsequently retrains the global classifier utilizing the shared features. The classifier retraining process enhances the model's understanding of the holistic view of the data distribution, ensuring better generalization across diverse datasets. This improved generalization enables the classifier to adaptively influence the feature extractor during subsequent local training epochs. We establish a balance between enhancing model accuracy and safeguarding individual privacy through the implementation of differential privacy mechanisms. By incorporating noise into the feature vectors shared with the server, we ensure that sensitive data remains confidential. We present a comprehensive convergence analysis, along with theoretical reasoning regarding performance enhancement and privacy preservation. We vali

Author

Gain, Mrityunjoy; Kim, Kitae; Raha, Avi Deb; Adhikary, Apurba; Huh, Eui-Nam; Han, Zhu; Hong, Choong Seon

Published

2025

Language

EN