DeepAI AI Chat
Log In Sign Up

AcME – Accelerated Model-agnostic Explanations: Fast Whitening of the Machine-Learning Black Box

by   David Dandolo, et al.

In the context of human-in-the-loop Machine Learning applications, like Decision Support Systems, interpretability 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. Not only does AcME compute 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.


page 26

page 36

page 37


Global Aggregations of Local Explanations for Black Box models

The decision-making process of many state-of-the-art machine learning mo...

Can I trust you more? Model-Agnostic Hierarchical Explanations

Interactions such as double negation in sentences and scene interactions...

Model-Agnostic Explainability for Visual Search

What makes two images similar? We propose new approaches to generate mod...

Beyond Importance Scores: Interpreting Tabular ML by Visualizing Feature Semantics

Interpretability is becoming an active research topic as machine learnin...

Comparing Feature Importance and Rule Extraction for Interpretability on Text Data

Complex machine learning algorithms are used more and more often in crit...

ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanations

The ever increasing complexity of machine learning techniques used more ...