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
Currently, the classifier is consistently trained over all global epochs. However, our pipeline schematic indicates that it should only be trained after all communication is done. Add the ability to re-initialize the server classifier's weights each round (essentially training from scratch each round) to see if this makes a difference at all.
Motivation: initial samples from the aggregated decoder may not be very high quality, which could direct classifier's weights towards a bad part of loss space.
The text was updated successfully, but these errors were encountered:
Currently, the classifier is consistently trained over all global epochs. However, our pipeline schematic indicates that it should only be trained after all communication is done. Add the ability to re-initialize the server classifier's weights each round (essentially training from scratch each round) to see if this makes a difference at all.
The text was updated successfully, but these errors were encountered: