Benefits of using multiple post-hoc explanations for Machine Learning

Corentin Boidot (1, 2, 3) , Olivier Augereau (4, 2, 1) , Pierre de Loor (2, 1, 4) , Riwal Lefort (5)

1 ENIB - École Nationale d'Ingénieurs de Brest
2 Lab-STICC_COMMEDIA - Equipe COgnition, Models and Machines for Engaging Digital Interactive Applications
3 Crédit Mutuel Arkéa
4 Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
5 Arkéa

EXplainable AI (XAI) offers a wide range of algorithmic solutions to the problem of AI's opacity, but ensuring of their usefulness remains a challenge. In this study, we propose an multi-explanation XAI system using surrogate rules, LIME and nearest neighbor on a random forest. Through an experiment in an e-sports prediction task, we demonstrate the feasibility and measure the usefulness of working with multiple forms of explanation. Considering users' preferences, we offer new perspectives for XAI design and evaluation, highlighting the concept of data difficulty and of the idea of prior agreement between users and AI.

Keywords: XAI

Domains: Artificial Intelligence [cs.AI]; Human-Computer Interaction [cs.HC]; Computer science

Corentin Boidot, Olivier Augereau, Pierre de Loor, Riwal Lefort. Benefits of using multiple post-hoc explanations for Machine Learning. 2023 International Conference on Machine Learning and Applications (ICMLA 2023 ))., Dec 2023, Jacksonville, United States. ⟨hal-04326199⟩