91 citations · 155 across the 11 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 7 cited
Understanding Interventional TreeSHAP : How and Why it Works
Gabriel Laberge, Yann Pequignot
Shapley values are ubiquitous in interpretable Machine Learning due to their strong theoretical background and efficient implementation in the SHAP library. Computing these values…
cs.LG2022★ 4 cited
Fool SHAP with Stealthily Biased Sampling
Gabriel Laberge, Ulrich Aïvodji, Satoshi Hara +2
SHAP explanations aim at identifying which features contribute the most to the difference in model prediction at a specific input versus a background distribution. Recent studies h…