A Novel Federated Transfer Learning Framework Based on Collaborative GAN for Smart Manufacturing

Smart manufacturing aims to support highly dynamic and flexible production processes where intelligent machines are expected to have the ability to complete quickly transition from old applications to new ones. Federated transfer learning is a promising solution that enables knowledge sharing in the above process to rapidly provide models required for new tasks. To achieve efficient transfer, the challenge lies in how to provide transferable and high-quality data for new tasks while preserving data privacy. In this paper, we propose a novel cross-application federated transfer learning framework based on collaborative generative adversarial networks named CPFTL-CGAN. Specifically, we innovatively propose a source domain selection scheme based on domain similarity, which aims to select the most optimal source domain among massive candidates for efficient knowledge sharing. Furthermore, a collaborative generative adversarial network has been designed to generate data similar to the source, which addresses the problem that private source domain data cannot be shared directly to the target domain and further enhances the quality of the generated data. Finally, domain adaptation based on generated data is performed on target clients. Extensive simulation results demonstrate that the proposed CPFTL-CGAN can effectively improve the learning efficiency and accuracy compared to single-device training locally, Fedavg and ACGAN-FTL.