FedDTG：基于三方生成对抗网络的无数据联邦知识蒸馏
FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks
AI总结：
本文提出基于三方生成对抗网络的无数据联邦知识蒸馏方法FedDTG，利用GAN生成伪造样本实现高效鲁棒的客户端互蒸馏，在保护隐私的同时获取全局知识，并在泛化能力上优于现有联邦蒸馏算法。
摘要：
尽管现有的联邦学习方法主要侧重于聚合本地模型以构建全局模型，但在实际场景中，由于包含隐私敏感信息，部分客户端可能不愿共享其私有模型。知识蒸馏可以在不访问模型参数的情况下提取模型知识，非常适用于这种联邦场景。然而，联邦学习中的大多数蒸馏方法（联邦蒸馏）需要代理数据集，这在现实世界中难以获取。因此，在本文中，我们引入分布式三方生成对抗网络（GAN）来实现无数据互蒸馏，并提出了一种名为FedDTG的有效方法。我们证实，GAN生成的伪造样本能够使联邦蒸馏更加高效和鲁棒。此外，客户端之间的蒸馏过程可以在保护数据隐私的同时获取全局知识，并带来良好的个体客户端性能。我们在基准视觉数据集上的大量实验表明，我们的方法在泛化能力上优于其他联邦蒸馏算法。
英文摘要：
While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusion of privacy-sensitive information. Knowledge distillation, which can extract model knowledge without accessing model parameters, is well-suited for this federated scenario. However, most distillation methods in federated learning (federated distillation) require a proxy dataset, which is difficult to obtain in the real world. Therefore, in this paper, we introduce a distributed three-player Generative Adversarial Network (GAN) to implement data-free mutual distillation and propose an effective method called FedDTG. We confirmed that the fake samples generated by GAN can make federated distillation more efficient and robust. Additionally, the distillation process between clients can deliver good individual client performance while simultaneously acquiring global knowledge and protecting data privacy. Our extensive experiments on benchmark vision datasets demonstrate that our method outperforms other federated distillation algorithms in terms of generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
