11 papers
ShaplEIG: Bayesian Experimental Design for Shapley Value Estimation
David Rundel, Fabian Fumagalli, Maximilian Muschalik +2
Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, moti…
Proxy-Based Approximation of Shapley and Banzhaf Interactions
Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter +3
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trad…
ConfoundingSHAP: Quantifying confounding strength in causal inference
Marie Brockschmidt, Santo M. A. R. Thies, Maresa Schröder +5
In causal inference, confounders are variables that influence both treatment decisions and outcomes. However, unlike as in randomized clinical trials, the treatment assignment mech…
Efficient Credal Prediction through Decalibration
Paul Hofman, Timo Löhr, Maximilian Muschalik +2
A reliable representation of uncertainty is essential for the application of modern machine learning methods in safety-critical settings. In this regard, the use of credal sets (i.…
Exactly Computing do-Shapley Values
R. Teal Witter, Ãlvaro Parafita, Tomas Garriga +4
Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapl…
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
Julia Herbinger, Gabriel Laberge, Maximilian Muschalik +3
Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree, producing conflicti…