You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi everyone. Can you create a tutorial example on how to use Stochastic Weight Averaging in Federated Learning, and in particular, with OpenFL? I think It is a really important tool to obtain good models, especially in the context of Transfer or Federated Learning, where we perform an average of the weights. To the best of my knowledge, 'til now I think that it is not implemented in any federated learning solutions.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi everyone. Can you create a tutorial example on how to use Stochastic Weight Averaging in Federated Learning, and in particular, with OpenFL? I think It is a really important tool to obtain good models, especially in the context of Transfer or Federated Learning, where we perform an average of the weights. To the best of my knowledge, 'til now I think that it is not implemented in any federated learning solutions.
Useful links:
1: original paper: https://arxiv.org/pdf/1803.05407.pdf
2. PyTorch blog and implementation: https://pytorch.org/blog/pytorch-1.6-now-includes-stochastic-weight-averaging/
Beta Was this translation helpful? Give feedback.
All reactions