Report
FedMCSA: Personalized Federated Learning via Model Components Self-Attention
| العنوان: | FedMCSA: Personalized Federated Learning via Model Components Self-Attention |
|---|---|
| المؤلفون: | Guo, Qi, Qi, Yong, Qi, Saiyu, Wu, Di, Li, Qian |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning |
| الوصف: | Federated learning (FL) facilitates multiple clients to jointly train a machine learning model without sharing their private data. However, Non-IID data of clients presents a tough challenge for FL. Existing personalized FL approaches rely heavily on the default treatment of one complete model as a basic unit and ignore the significance of different layers on Non-IID data of clients. In this work, we propose a new framework, federated model components self-attention (FedMCSA), to handle Non-IID data in FL, which employs model components self-attention mechanism to granularly promote cooperation between different clients. This mechanism facilitates collaboration between similar model components while reducing interference between model components with large differences. We conduct extensive experiments to demonstrate that FedMCSA outperforms the previous methods on four benchmark datasets. Furthermore, we empirically show the effectiveness of the model components self-attention mechanism, which is complementary to existing personalized FL and can significantly improve the performance of FL. Comment: The first submission of this work is to AAAI2022 in 20210829. Now the new submission for review |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2208.10731 |
| رقم الانضمام: | edsarx.2208.10731 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |