Adapted Weighted Aggregation in Federated Learning

Yitong Tang

doi:10.1609/aaai.v38i21.30557

Adapted Weighted Aggregation in Federated Learning

Authors

Yitong Tang University of British Columbia, 2329 West Mall Trusted and Efficient AI (TEA) Lab

DOI:

https://doi.org/10.1609/aaai.v38i21.30557

Keywords:

Fairness, Federated, FedAW, Computer Vision

Abstract

This study introduces FedAW, a novel federated learning algorithm that uses a weighted aggregation mechanism sensitive to the quality of client datasets, leading to better model performance and faster convergence on diverse datasets, validated using Colored MNIST.

AAAI-24 / IAAI-24 / EAAI-24 Proceedings Cover

Downloads

Published

2024-03-24

How to Cite

Tang, Y. (2024). Adapted Weighted Aggregation in Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23763-23765. https://doi.org/10.1609/aaai.v38i21.30557