PaDPaF：部分联邦GAN的部分解耦
PaDPaF: Partial Disentanglement with Partially-Federated GANs
AI总结：
提出PaDPaF架构，通过部分联邦GAN隐式解耦内容与风格，实现个性化生成和隐私保护，实验验证其有效性。
摘要：
联邦学习已成为一种流行的机器学习范式，具有许多潜在的实际应用，包括推荐系统、物联网（IoT）、医疗保健和自动驾驶。尽管目前大多数应用侧重于基于分类的任务，但学习个性化生成模型在很大程度上仍未得到探索，并且它们在异构环境中的优势仍需更好地理解。这项工作提出了一种新颖的架构，结合了全局客户端无关和局部客户端特定的生成模型。我们表明，使用标准技术训练联邦模型，我们提出的模型通过隐式解耦全局一致表示（即内容）与客户端相关变化（即风格）来实现隐私和个性化。利用这种分解，个性化模型可以生成本地未见过的标签，同时保留给定客户端的风格，并且通过训练一个简单的线性分类器在全局内容特征上，可以高精度地预测所有客户端的标签。此外，解耦通过仅共享内容来实现其他重要应用，如数据匿名化。广泛的实验评估证实了我们的发现，并且我们还讨论了所提出方法的理论动机。
英文摘要：
Federated learning has become a popular machine learning paradigm with many potential real-life applications, including recommendation systems, the Internet of Things (IoT), healthcare, and self-driving cars. Though most current applications focus on classification-based tasks, learning personalized generative models remains largely unexplored, and their benefits in the heterogeneous setting still need to be better understood. This work proposes a novel architecture combining global client-agnostic and local client-specific generative models. We show that using standard techniques for training federated models, our proposed model achieves privacy and personalization by implicitly disentangling the globally consistent representation (i.e. content) from the client-dependent variations (i.e. style). Using such decomposition, personalized models can generate locally unseen labels while preserving the given style of the client and can predict the labels for all clients with high accuracy by training a simple linear classifier on the global content features. Furthermore, disentanglement enables other essential applications, such as data anonymization, by sharing only the content. Extensive experimental evaluation corroborates our findings, and we also discuss a theoretical motivation for the proposed approach.
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。
