Robust aggregation for federated learning by minimum -divergence estimation

HIGHLIGHTS

• who: Cen-Jhih Li and collaborators from the Taiwan University, Taipei City, Taiwan have published the research: Robust Aggregation for Federated Learning by Minimum -Divergence Estimation, in the Journal: Entropy 2022, 24, 686. of /2022/
• what: The authors propose an alternative robust aggregation method named u03b3-mean which is the minimum based on a robust density power This u03b3-mean aggregation mitigates the influence of Byzantine clients by assigning fewer weights. The goal is to minimize the following objective function: m L(u03b8 )= u2211 u03c0i Eu03b7i ~D , i=1 where u03b8 u2208 R p is . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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