Recently I came along the paper Robust and Stable Black Box Explanations, which discusses a nice framework for global model-agnostic explanations.
I was thinking to recreate the experiments performed in the paper, but unfortunately authors haven't provided the code. The summary of the experiments are :
use LIME, SHAP and MUSE as baseline models, and compute fidelity score on test data. (All the 3 datasets are used for classification problems)
since LIME and SHAP give local explanations, for a particular data point, the idea is to use K points from the training dataset, and create K explanations using LIME. LIME is supposed to return a local linear explanation. Now, for a new test data point, using the nearest point from K points used earlier and use the corresponding explanation to classify this new point.
measure the performance, using fidelity score (% of points for which E(x) = B(x), where E(x) is the explanation of the point and B(x) is the classification of the point using black box.
Now, the issue is, I am using LIME and SHAP packages in Python to achieve the results on baseline models. But, I am not sure how I'll get linear explanation for a point (one from the set K), and use to to classify a new test point in the neighborhood. Every tutorial on YouTube and Medium, discusses about visualizing the explanation for a given point but none talks about how to get the linear model itself and use it for newer points.