Theoretical Evaluation of Asymmetric Shapley Values for Root-Cause Analysis

Kelen, Domokos; Petreczky, Mihàly; Kersch, Péter; Benczúr, Andràs

Document type :

Communication dans un congrès avec actes

DOI :

10.1109/ICDM58522.2023.00030

Title :

Theoretical Evaluation of Asymmetric Shapley Values for Root-Cause Analysis

Author(s) :

Kelen, Domokos [Auteur]
Institute for Computer Science and Control [Budapest] [SZTAKI]
Petreczky, Mihàly [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Kersch, Péter [Auteur]
Ericsson [Budapest]
Benczúr, Andràs [Auteur]
Institute for Computer Science and Control [Budapest] [SZTAKI]

Conference title :

2023 IEEE International Conference on Data Mining (ICDM)

City :

Shanghai

Country :

Chine

Start date of the conference :

2023-12-01

Book title :

2023 IEEE International Conference on Data Mining (ICDM)

Publisher :

IEEE

English keyword(s) :

explainability SHAP causality
explainability
SHAP
causality

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

In this work, we examine Asymmetric Shapley Values (ASV), a variant of the popular SHAP additive local explanation method. ASV proposes a way to improve model explanations incorporating known causal relations between ...
Show more >In this work, we examine Asymmetric Shapley Values (ASV), a variant of the popular SHAP additive local explanation method. ASV proposes a way to improve model explanations incorporating known causal relations between variables, and is also considered as a way to test for unfair discrimination in model predictions. Unexplored in previous literature, relaxing symmetry in Shapley values can have counter-intuitive consequences for model explanation. To better understand the method, we first show how local contributions correspond to global contributions of variance reduction. Using variance, we demonstrate multiple cases where ASV yields counter-intuitive attributions, arguably producing incorrect results for root-cause analysis. Second, we identify generalized additive models (GAM) as a restricted class for which ASV exhibits desirable properties. We support our arguments by proving multiple theoretical results about the method. Finally, we demonstrate the use of asymmetric attributions on multiple real-world datasets, comparing the results with and without restricted model families using gradient boosting and deep learning models.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

document
Open access
Access the document

2310.09961.pdf
Open access
Access the document

document
Open access
Access the document

2310.09961.pdf
Open access
Access the document

Theoretical Evaluation of Asymmetric Shapley ... BibTeX CSV Excel RIS

Files

Theoretical Evaluation of Asymmetric Shapley ...

BibTeX

CSV

Excel

RIS