Sobol-based Sensitivity Analysis NeurIPS 2023

$$ S_i = \text{cross\_entropy}(f(\mathbf{x}), f(\mathbf{x}_{-i})), $$

where $S_i$ represents the importance scores of the $i$-th feature. In contrast, this paper computes $S_i$ based on Sobol indices.

$$ \Phi(\mathbf{x}, \mathbf{M}) = \mathbf{x} \odot \mathbf{M} + (1 - \mathbf{M}) \odot 0 $$

In this paper, the function is defined similarly to existing literature but is referred to as Inpainting perturbation.

References

NeurIPS 2021 Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis