Federated Transfer Learning Based Cross-Domain Prediction for Smart Manufacturing

DOI PDF 被引用文献2件 オープンアクセス

この論文をさがす

説明

In this paper, a new federated transfer learning framework, FTL-CDP, is proposed to address the challenges of data scarcity and data privacy faced by modern smart manufacturing with cross-domain applications. Existing applications can share their knowledge through the central server as base models, while new applications can convert a base model to their target domain models with limited application-specific data using transfer learning technique. Meanwhile, the federated learning scheme is deployed among smart devices within the same group to further enhance the accuracy of the application-specific model. The integrated framework allows model sharing across the central server and different smart devices without exposing any raw data, and hence protects data privacy. Two public datasets COCO and PETS2009, which represent the source and target applications, are employed for evaluations. The simulation results show that the proposed method outperforms two state-of-the-art machine learning approaches, by achieving better learning efficiency and accuracy.

収録刊行物

被引用文献 (2)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ