Brainstorming Generative Adversarial Networks (BGANs): Towards Multi-Agent Generative Models with Distributed Private Datasets
This addresses the challenge of multi-agent generative modeling with privacy and communication constraints, offering a scalable solution without centralized control, though it appears incremental as an extension of distributed GAN methods.
The paper tackles the problem of training generative adversarial networks (GANs) with limited and distributed private datasets across multiple agents, proposing a fully distributed brainstorming GAN (BGAN) architecture that allows agents to share generated samples instead of real data, resulting in higher-quality samples with lower Jensen-Shannon divergence and Frèchet Inception distance compared to other distributed GANs.
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.