摘要
In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, inter-pretability approaches should provide actionable insights without making the users wait. In this paper, we propose Accelerated Model-agnostic Explanations (AcME), an interpretability approach that quickly provides feature importance scores both at the global and the local level. AcME can be applied a posteriori to each regression or classification model based on tabular data. Not only AcME computes feature ranking, but it also provides a what-if analysis tool to assess how changes in features values would affect model predictions. We evaluated the proposed approach on synthetic and real-world datasets, also in comparison with SHapley Additive exPlanations (SHAP), the approach we drew inspiration from, which is currently one of the state-of-the-art model-agnostic interpretability approaches. We achieved comparable results in terms of quality of produced explanations while reducing dramatically the computational time and providing consistent visualization for global and local interpretations. To foster research in this field, and for the sake of reproducibility, we also provide a repository with the code used for the experiments.
学科与关键词
- A review and benchmark of feature importance methods for neural networksMandler, Hannes*; Weigand, BernhardACM Computing Surveys, 2024, 56(12): 318.
- To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methodsAmparore, Elvio*; Perotti, Alan; Bajardi, PaoloPeerJ Computer Science, 2021, e479.被引 40
- The coming of age of interpretable and explainable machine learning modelsLisboa, P. J. G.; Saralajew, S.; Vellido, A.; Fernandez-Domenech, R.; Villmann, T.*NEUROCOMPUTING, 2023, 535: 25-39.被引 35
