Open xitefanjisi opened 4 years ago
I am noticing the same thing
We had a similar problem when using this method for selection of EEG channels. We were able to reduce the number of duplicate selections by adding a regularization term to the loss, which penalizes such duplicates. Paper here: https://homes.esat.kuleuven.be/~abertran/reports/TS_JNE_2021.pdf Github: https://github.com/AlexanderBertrandLab/Gumbel-Channel-Selection
In my experience, replicated features are caused by not having enough number of epochs to converge. When I was running experiments for the ICML paper, when I set the hyperparameters right, I never observed replicated features selected.
Thank you for your great feature selection method. However, I found that your method might lead to such a situation that the same features could be selected for multiple times. For example, after training, the method
get_support()
might output a result like[3, 4, 6, 2, 2, 5, 1, 0]
. In this case, the second feature has been selected twice. Is it possible to avoid such cases using concrete autoencoders? Thank you!