Why extra_features not used in the regressor?

[Antoninnnn]

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.)

[cvignac]

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.