تقرير
Federated Learning with Fair Averaging
العنوان: | Federated Learning with Fair Averaging |
---|---|
المؤلفون: | Wang, Zheng, Fan, Xiaoliang, Qi, Jianzhong, Wen, Chenglu, Wang, Cheng, Yu, Rongshan |
سنة النشر: | 2021 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning |
الوصف: | Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency. The source code is available at https://github.com/WwZzz/easyFL. Comment: Accepted by IJCAI2021 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2104.14937 |
رقم الأكسشن: | edsarx.2104.14937 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |