[nu91]

I am curious to know if this type of network can help with causal inference.

[esafak]

They help with interpretability, which is a step brother. See for example "From Shapley Values to Generalized Additive Models and back" https://arxiv.org/abs/2209.04012

[nu91]

Indeed, Thank you!

[fermisea]

They definitely do, I'm planning to release a new package to do that in a couple weeks