Why isn't the loss calculated only with b_i=0 values of the Hints. about gain HOT 2 CLOSED

Thanks for your interest in our work.
First, yes. you are correct. We calculate the loss for the components with hint and without hint.
There are pros and cons to do this.

• Cons: As you said, it may overfit to the hint.
• Pros: It helps discriminator to utilize the hint more explicitly.

For the cons, we think that only with hint, the discriminator cannot solve the task perfectly; thus, we think it may not only just overfit on the hint.

Therefore, we focus more on pros and use this as the official implementation.

Thanks!

from gain.

Thank you very much for your answer! It has been helpful.

from gain.