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
Do you mean the Eq. 15? I see in your code that the S matrix is calculated by B_attr = labels_attribute * (eta - 1) +1. diff_attribute = tf.square(tf.subtract(preds_attribute, labels_attribute) * B_attr)
So, i think when the eta = 1, it means the S is not added. So is the theta
I'm wondering if theta = eta = 1 means the original ComGA. Otherwise, if the theta and eta are greater than 1 means the ComGA-O?
The text was updated successfully, but these errors were encountered: