EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations
This work addresses interpretability challenges for users of complex ML models, particularly in industrial applications like defect detection, but it is incremental as it builds on existing LIME methods.
The authors tackled the problem of explaining black-box machine learning models by proposing EBLIME, which uses Bayesian ridge regression to obtain feature importance distributions, resulting in more intuitive and accurate outcomes with improved uncertainty quantification compared to state-of-the-art methods.
We propose EBLIME to explain black-box machine learning models and obtain the distribution of feature importance using Bayesian ridge regression models. We provide mathematical expressions of the Bayesian framework and theoretical outcomes including the significance of ridge parameter. Case studies were conducted on benchmark datasets and a real-world industrial application of locating internal defects in manufactured products. Compared to the state-of-the-art methods, EBLIME yields more intuitive and accurate results, with better uncertainty quantification in terms of deriving the posterior distribution, credible intervals, and rankings of the feature importance.