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

作     者：Hedström, Anna Weber, Leander Lapuschkin, Sebastian Höhne, Marina 

作者机构：Department of Electrical Engineering and Computer Science TU Berlin Germany Department of Artificial Intelligence Fraunhofer Heinrich Hertz Institute Berlin Germany  Germany BIFOLD Berlin Institute for the Foundations of Learning and Data Germany Department of Computer Science University of Potsdam Germany 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

摘      要：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. © 2024, CC BY-NC-SA.