Abstract Interpretation-Based Feature Importance for SVMs

no code implementations • 22 Oct 2022 • Abhinandan Pal, Francesco Ranzato, Caterina Urban, Marco Zanella

We leverage this abstraction in two ways: (1) to enhance the interpretability of SVMs by deriving a novel feature importance measure, called abstract feature importance (AFI), that does not depend in any way on a given dataset of the accuracy of the SVM and is very fast to compute, and (2) for verifying stability, notably individual fairness, of SVMs and producing concrete counterexamples when the verification fails.

Fairness Feature Importance