KEYWORDS: Data modeling, Machine learning, Statistical modeling, Performance modeling, Education and training, Data privacy, Matrices, Deep learning, Stochastic processes, Process modeling
Federated learning is mainly to solve the problem of data privacy in distributed machine learning, but the current non independent and identically distributed (non-iid) data poses a serious challenge to federated learning, which not only destroys the performance of the global model, but also affects the personalized features of the local model more importantly. In this paper, we try to keep local personalization by an idea of adding a private model locally for knowledge transfer to the local model, in addition, we also combine a kind of matching the probability distributions of the data of the two models in the feature space to do the knowledge transfer, which can improve the effect of personalization of the local model as well as improve the performance of the global model more effectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.