A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
Hi, I'm wondering if the multi-input attribution models can be targeted to specific neutrons for e.g., correct/incorrect class. In the single input models you can specify a ys=ys, but in the examples for the multi-input models, this doesn't appear to be the case, and throws an error. Am I missing something obvious :S
Could you please report the error and the code that you are using?
Notice that instead of passing ys you can mask the target tensor directly (eg. target = original_target * ys)... maybe this help in your case.
Hi, I'm wondering if the multi-input attribution models can be targeted to specific neutrons for e.g., correct/incorrect class. In the single input models you can specify a ys=ys, but in the examples for the multi-input models, this doesn't appear to be the case, and throws an error. Am I missing something obvious :S