A Prototype Towards Modeling Visual Data Using Decentralized Generative Adversarial Networks

Decentralized computation is crucial for training on large data sets, which are stored in various locations. This paper proposes a method for collaboratively training generative adversarial networks (GANs) on several nodes to approach this problem. Each node has access to its local private dataset and model, but can influence and can be influenced by neighboring nodes. Such an approach avoids the need of a fusion center, offers better network load balance, higher robustness to network errors and improves data privacy. This work proposes an initial approach for decentralized GAN network optimization which is based on discriminator exchange among neighbors using an information gain criterion. We present our initial experiments to verify whether such a decentralized architecture can provide useful results.