Saved in:
Bibliographic Details
Main Authors: Chowdhury, Sujit, Halder, Raju
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.03862
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915082900865024
author Chowdhury, Sujit
Halder, Raju
author_facet Chowdhury, Sujit
Halder, Raju
contents Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed machine learning, but faces challenges with heterogeneous data distributions across clients. This paper presents FedSat, a novel FL approach specifically designed to simultaneously handle three forms of data heterogeneity, namely label skewness, missing classes, and quantity skewness, by proposing a prediction-sensitive loss function and a prioritized-class based weighted aggregation scheme. While the prediction-sensitive loss function enhances model performance on minority classes, the prioritized-class based weighted aggregation scheme ensures client contributions are weighted based on both statistical significance and performance on critical classes. Extensive experiments across diverse data-heterogeneity settings demonstrate that FedSat significantly outperforms state-of-the-art baselines, with an average improvement of 1.8% over the second-best method and 19.87% over the weakest-performing baseline. The approach also demonstrates faster convergence compared to existing methods. These results highlight FedSat's effectiveness in addressing the challenges of heterogeneous federated learning and its potential for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03862
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FedSat: A Statistical Aggregation Approach for Class Imbalanced Clients in Federated Learning
Chowdhury, Sujit
Halder, Raju
Machine Learning
Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed machine learning, but faces challenges with heterogeneous data distributions across clients. This paper presents FedSat, a novel FL approach specifically designed to simultaneously handle three forms of data heterogeneity, namely label skewness, missing classes, and quantity skewness, by proposing a prediction-sensitive loss function and a prioritized-class based weighted aggregation scheme. While the prediction-sensitive loss function enhances model performance on minority classes, the prioritized-class based weighted aggregation scheme ensures client contributions are weighted based on both statistical significance and performance on critical classes. Extensive experiments across diverse data-heterogeneity settings demonstrate that FedSat significantly outperforms state-of-the-art baselines, with an average improvement of 1.8% over the second-best method and 19.87% over the weakest-performing baseline. The approach also demonstrates faster convergence compared to existing methods. These results highlight FedSat's effectiveness in addressing the challenges of heterogeneous federated learning and its potential for real-world applications.
title FedSat: A Statistical Aggregation Approach for Class Imbalanced Clients in Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2407.03862