Implementation bug of fedprox

SMILELab-FL / FedLab

A flexible Federated Learning Framework based on PyTorch, simplifying your Federated Learning research.

https://fedlab.readthedocs.io

Apache License 2.0

743 stars 127 forks source link

Implementation bug of fedprox #280

Closed KPollux closed 2 years ago

KPollux commented 2 years ago

Describe the bug In fedlab/contrib/algorithm/fedprox.py Line 59, 60. The loss calculation code seems to mistakenly override the correct implementation of fedprox.

dunzeng commented 2 years ago

Yes, it is a mistake. We will fix it later. Thank you so much.