Paper ID: 2301.08086

Shapley Values with Uncertain Value Functions

Raoul Heese, Sascha Mücke, Matthias Jakobs, Thore Gerlach, Nico Piatkowski

We propose a novel definition of Shapley values with uncertain value functions based on first principles using probability theory. Such uncertain value functions can arise in the context of explainable machine learning as a result of non-deterministic algorithms. We show that random effects can in fact be absorbed into a Shapley value with a noiseless but shifted value function. Hence, Shapley values with uncertain value functions can be used in analogy to regular Shapley values. However, their reliable evaluation typically requires more computational effort.

Submitted: Jan 19, 2023