specified_masks_mask_generator {shapr} | R Documentation |
A torch::nn_module()
Representing a specified_masks_mask_generator
Description
A mask generator which masks the entries based on sampling provided 1D masks with corresponding probabilities. Used for Shapley value estimation when only a subset of coalitions are used to compute the Shapley values.
Usage
specified_masks_mask_generator(masks, masks_probs, paired_sampling = FALSE)
Arguments
masks |
Matrix/Tensor of possible/allowed 'masks' which we sample from. |
masks_probs |
Array of 'probabilities' for each of the masks specified in 'masks'. Note that they do not need to be between 0 and 1 (e.g. sampling frequency). They are scaled, hence, they only need to be positive. |
paired_sampling |
Boolean. If we are doing paired sampling. So include both S and |
Author(s)
Lars Henry Berge Olsen