Does Dataset Complexity Matters for Model Explainers?
This work addresses the lack of consensus in XAI for practitioners by benchmarking tools on tabular data, though it is incremental as it focuses on existing methods applied to new datasets.
The study investigated whether dataset complexity affects the consistency of explanations from different XAI measures, finding that results from 82 models and 592 ranks highlight dataset complexity as a key factor in explainability.
Strategies based on Explainable Artificial Intelligence - XAI have emerged in computing to promote a better understanding of predictions made by black box models. Most XAI measures used today explain these types of models, generating attribute rankings aimed at explaining the model, that is, the analysis of Attribute Importance of Model. There is no consensus on which XAI measure generates an overall explainability rank. For this reason, several proposals for tools have emerged (Ciu, Dalex, Eli5, Lofo, Shap and Skater). An experimental benchmark of explainable AI techniques capable of producing global explainability ranks based on tabular data related to different problems and ensemble models are presented herein. Seeking to answer questions such as "Are the explanations generated by the different measures the same, similar or different?" and "How does data complexity play along model explainability?" The results from the construction of 82 computational models and 592 ranks shed some light on the other side of the problem of explainability: dataset complexity!