Explainable Global Fairness Verification of Tree-Based Classifiers
This addresses fairness verification for tree-based classifiers, providing explainable guarantees for all inputs, which is incremental as it builds on existing verification methods.
The paper tackles the problem of verifying global fairness in tree-based classifiers by synthesizing understandable propositional logic formulas as sufficient conditions for fairness, and demonstrates its approach is precise, explainable, and efficient on public datasets.
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.