Perhefed: a general framework of personalized federated learning for heterogeneous convolutional neural networks

HIGHLIGHTS

• who: Ma from the (UNIVERSITY) have published the Article: PerHeFed: A general framework of personalized federated learning for heterogeneous convolutional neural networks, in the Journal: (JOURNAL)
• what: The authors propose a general framework for personalized federated learning (PerHeFed) which enables the devices to design their local model structures autonomously and share sub-models without structural restrictions. The authors show in Table 1 the comparison of PerHeFed with other state-of-the-art methods in terms of support for local model and shared model heterogeneity, each of which is subdivided into inter-layer heterogeneity and intra . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.