头脑风暴生成对抗网络（BGANs）：面向分布式私有数据集的多智能体生成模型
Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
AI总结：
本文提出头脑风暴生成对抗网络（BGAN），使多个智能体在完全分布式且不共享真实数据的情况下，通过交换生成样本协作学习数据分布，理论证明其纳什均衡，实验显示生成质量优于现有分布式GAN。
摘要：
为了实现较高的学习精度，生成对抗网络（GANs）必须由能够充分表示数据空间的大型数据集来训练。然而，在许多场景中，可用数据集可能有限且分布在多个智能体之间，每个智能体都试图独立学习数据分布。在此类场景中，智能体通常不愿共享其本地数据，因为大型数据集的共享会造成通信开销。为了解决这一多智能体GAN问题，本文提出了一种新颖的头脑风暴GAN（BGAN）架构，多个智能体可以在完全分布式的方式下运行，同时生成逼真的数据样本。BGAN允许智能体在不共享真实数据集的情况下从其他智能体获取信息，而是通过共享其生成的数据样本进行“头脑风暴”。与现有的分布式GAN解决方案相比，所提出的BGAN架构被设计为完全分布式，不需要任何集中式控制器。此外，BGAN被证明具有可扩展性，并且不依赖于智能体深度神经网络（DNNs）的超参数，从而使智能体能够具有不同的DNN架构。在理论上，BGAN智能体之间的交互被分析为一个博弈，并推导出其唯一的纳什均衡。实验结果表明，与其他分布式GAN架构相比，BGAN能够生成质量更高、Jensen-Shannon散度（JSD）和Fréchet Inception距离（FID）更低的逼真数据样本。
英文摘要：
To achieve a high learning accuracy, generative adversarial networks (GANs) must be fed by large datasets that adequately represent the data space. However, in many scenarios, the available datasets may be limited and distributed across multiple agents, each of which is seeking to learn the distribution of the data on its own. In such scenarios, the agents often do not wish to share their local data as it can cause communication overhead for large datasets. In this paper, to address this multi-agent GAN problem, a novel brainstorming GAN (BGAN) architecture is proposed using which multiple agents can generate real-like data samples while operating in a fully distributed manner. BGAN allows the agents to gain information from other agents without sharing their real datasets but by ``brainstorming'' via the sharing of their generated data samples. In contrast to existing distributed GAN solutions, the proposed BGAN architecture is designed to be fully distributed, and it does not need any centralized controller. Moreover, BGANs are shown to be scalable and not dependent on the hyperparameters of the agents' deep neural networks (DNNs) thus enabling the agents to have different DNN architectures. Theoretically, the interactions between BGAN agents are analyzed as a game whose unique Nash equilibrium is derived. Experimental results show that BGAN can generate real-like data samples with higher quality and lower Jensen-Shannon divergence (JSD) and Frèchet Inception distance (FID) compared to other distributed GAN architectures.
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。
