TsingZ0 / PFLlib

37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 20 datasets.
GNU General Public License v2.0
1.5k stars 310 forks source link

Some issue about FedProx #112

Closed Pengxin-Guo closed 1 year ago

Pengxin-Guo commented 1 year ago

In ths clientprox.py, is there a problem with the calculation of loss in lines 47-49,? Shouldn't we use the loss calculation method in lines 82-86?

TsingZ0 commented 1 year ago

Sorry for the delayed response. I have been quite busy recently.

Please note line 19, where a specific optimizer PerturbedGradientDescent is used to accelerate training.

yokinglee718 commented 1 year ago

Hello, for algorithms like FedProx and SCAFFOLD, the special optimizer they use is not as effective as the Adam optimizer I used in other algorithms. Can this be used as a comparative experiment?

TsingZ0 commented 1 year ago

Sure, you can adopt any optimizer as you want by modifying their codes and study whether other optimizers are more suitable.