SHAP-IQ: Unified Approximation of Any-Order Shapley Interactions
MCML Authors
Maximilian Muschalik
Patrick Kolpaczki
Eyke Hüllermeier
Prof. Dr.
Principal Investigator
Abstract
Maximilian Muschalik
Patrick Kolpaczki
Eyke Hüllermeier
Prof. Dr.
Principal Investigator
Abstract
Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interaction indices extend the SV to define any-order feature interactions. Defining a unique Shapley interaction index is an open research question and, so far, three definitions have been proposed, which differ by their choice of axioms. Moreover, each definition requires a specific approximation technique. Here, we propose SHAPley Interaction Quantification (SHAP-IQ), an efficient sampling-based approximator to compute Shapley interactions for arbitrary cardinal interaction indices (CII), i.e. interaction indices that satisfy the linearity, symmetry and dummy axiom. SHAP-IQ is based on a novel representation and, in contrast to existing methods, we provide theoretical guarantees for its approximation quality, as well as estimates for the variance of the point estimates. For the special case of SV, our approach reveals a novel representation of the SV and corresponds to Unbiased KernelSHAP with a greatly simplified calculation. We illustrate the computational efficiency and effectiveness by explaining language, image classification and high-dimensional synthetic models.
inproceedings
NeurIPS 2023
37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023.
Authors
F. Fumagalli • M. Muschalik • P. Kolpaczki • E. Hüllermeier • B. HammerLinks
URLResearch Area
BibTeXKey: FMK+23