Preserving Accuracy in Federated Learning via Equitable Model and Efficient Aggregation
Conference paper
Authors | Mehdi, M., Makkar, A., Conway, M. and Sama. L |
---|---|
Type | Conference paper |
Abstract | Machine learning has revolutionized research by extracting complicated patterns from complex data, particularly in healthcare and medical imaging, where accurate diagnosis is critical. The concept of federated learning has gained popularity in the field of machine learning as a viable technique for addressing privacy issues in distributed settings. This research explores federated learning in healthcare, demonstrating its capability to achieve results comparable to centralized data while enhancing the accuracy of deep learning models for clinical data interpretation. To ensure reliable model performance during federated learning rounds, this study introduces a proactive mechanism for coordinating server updates with equitable client modifications. The equitable model, designed to reduce accuracy fluctuations, consistently improves accuracy across multiple training rounds on a non-IID dataset. We achieved smooth accuracy improvement by implementing the novel Equitable model, resulting in robust model development. |
Keywords | Federated Learning; Fair Aggregation; Client updates; Equitable Model; Efficient Aggregation |
Year | 2024 |
Conference | International Conference on Recent Trends in Image Processing and Pattern Recognition |
Publisher | Springer Nature |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-53082-1_7 |
Web address (URL) | https://link.springer.com/chapter/10.1007/978-3-031-53082-1_7 |
Accepted author manuscript | License All rights reserved File Access Level Controlled |
Publisher's version | License All rights reserved File Access Level Restricted |
ISBN | 978-3-031-53082-1 |
Web address (URL) of conference proceedings | https://link.springer.com/chapter/10.1007/978-3-031-53082-1_7#chapter-info |
Output status | Published |
Publication dates | |
Online | 31 Jan 2024 |
Publication process dates | |
Accepted | 2023 |
Deposited | 18 Mar 2024 |
https://repository.derby.ac.uk/item/q5139/preserving-accuracy-in-federated-learning-via-equitable-model-and-efficient-aggregation
Restricted files
Accepted author manuscript
18
total views2
total downloads0
views this month0
downloads this month