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,
first of all thanks for sharing your code. I was trying to reproduce the results presented in the paper for the Amazon experiment, but I realized that when setting lambda=0.0 and/or adversarial_representation=False the numerical results for the risk do not change at all.
adversarial_representation=True
adversarial_representation=False
The text was updated successfully, but these errors were encountered:
Thanks @pmorerio for raising this. With some combinations of datasets/parameters, the adversarial component has more or less influence on the final result. Note also that the experiment results on the paper are not necessarily obtained with the same parameters (but chosen by the reverse validation procedure) for DANN and standard NN.
I changed the default example parameters to present a case where the adversarial component is more effective.
Hi,
first of all thanks for sharing your code. I was trying to reproduce the results presented in the paper for the Amazon experiment, but I realized that when setting
lambda=0.0
and/oradversarial_representation=False
the numerical results for the risk do not change at all.adversarial_representation=True
adversarial_representation=False
The text was updated successfully, but these errors were encountered: