ML Anthology

Adapted Weighted Aggregation in Federated Learning

Yitong Tang
AAAI 2024 pp. 23763-23765
doi:10.1609/AAAI.V38I21.30557 /aaai/2024/tang2024aaai-adapted/

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.

PDF AAAI Semantic Scholar

Cite

Text

Tang. "Adapted Weighted Aggregation in Federated Learning." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30557

Markdown

[Tang. "Adapted Weighted Aggregation in Federated Learning." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/tang2024aaai-adapted/) doi:10.1609/AAAI.V38I21.30557

BibTeX

@inproceedings{tang2024aaai-adapted,
  title     = {{Adapted Weighted Aggregation in Federated Learning}},
  author    = {Tang, Yitong},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23763-23765},
  doi       = {10.1609/AAAI.V38I21.30557},
  url       = {https://mlanthology.org/aaai/2024/tang2024aaai-adapted/}
}