Explainable Global Fairness Verification of Tree-Based ClassifiersDownload PDF

24 Aug 2022, 08:18 (modified: 18 Nov 2022, 01:16)SaTML 2023Readers: Everyone
Abstract: We present a new approach to the global fairness verification of tree-based classifiers. Given a tree-based classifier and a set of sensitive features potentially leading to discrimination, our analysis synthesizes sufficient conditions for fairness, expressed as a set of traditional propositional logic formulas, which are readily understandable by human experts. The verified fairness guarantees are global, in that the formulas predicate over all the possible inputs of the classifier, rather than just a few specific test instances. Our analysis is formally proved both sound and complete. Experimental results on public datasets show that the analysis is precise, explainable to human experts and efficient enough for practical adoption.
0 Replies