cvignac / DiGress

code for the paper "DiGress: Discrete Denoising diffusion for graph generation"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why extra_features not used in the regressor?

Antoninnnn opened this issue · comments

Is it because the effectiveness of the gradient $\nabla_{G_{t}}||y'-y||^{2}$? (We notice that extra_features are commonly used in the unconditional denoising model.)

The reason is that, as you mentioned, we need to take the gradient of the regressor with respect ot the noisy graph. We cannot differentiate through the extra features, so we prefer the regressor not to rely on them.