Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test

The Model Parameter Randomisation Test (MPRT) is widely acknowledged in the eXplainable Artificial Intelligence (XAI) community for its well-motivated evaluative principle: that the explanation function should be sensitive to changes in the parameters of the model function. However, recent works hav...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Hedström, Anna, Weber, Leander, Lapuschkin, Sebastian, Marina MC Höhne
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.01.2024
Subjects
Explainable artificial intelligence
Mathematical models
Model testing
Parameter identification
Parameter sensitivity
Randomization
Online AccessGet full text

Cover

More Information
Summary:The Model Parameter Randomisation Test (MPRT) is widely acknowledged in the eXplainable Artificial Intelligence (XAI) community for its well-motivated evaluative principle: that the explanation function should be sensitive to changes in the parameters of the model function. However, recent works have identified several methodological caveats for the empirical interpretation of MPRT. To address these caveats, we introduce two adaptations to the original MPRT -- Smooth MPRT and Efficient MPRT, where the former minimises the impact that noise has on the evaluation results through sampling and the latter circumvents the need for biased similarity measurements by re-interpreting the test through the explanation's rise in complexity, after full parameter randomisation. Our experimental results demonstrate that these proposed variants lead to improved metric reliability, thus enabling a more trustworthy application of XAI methods.
ISSN:2331-8422