تقرير
DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
العنوان: | DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning |
---|---|
المؤلفون: | Luo, Kangyang, Wang, Shuai, Fu, Yexuan, Li, Xiang, Lan, Yunshi, Gao, Ming |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
الوصف: | Federated Learning (FL) is a privacy-constrained decentralized machine learning paradigm in which clients enable collaborative training without compromising private data. However, how to learn a robust global model in the data-heterogeneous and model-heterogeneous FL scenarios is challenging. To address it, we resort to data-free knowledge distillation to propose a new FL method (namely DFRD). DFRD equips a conditional generator on the server to approximate the training space of the local models uploaded by clients, and systematically investigates its training in terms of fidelity, transferability} and diversity. To overcome the catastrophic forgetting of the global model caused by the distribution shifts of the generator across communication rounds, we maintain an exponential moving average copy of the generator on the server. Additionally, we propose dynamic weighting and label sampling to accurately extract knowledge from local models. Finally, our extensive experiments on various image classification tasks illustrate that DFRD achieves significant performance gains compared to SOTA baselines. Comment: Published as a conference paper at NeurIPS 2023 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2309.13546 |
رقم الأكسشن: | edsarx.2309.13546 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |