Abstracting Fairness: Oracles, Metrics, and Interpretability
This work addresses fairness evaluation in machine learning, particularly for high-stakes decisions like loan applications, by providing a method to abstract and interpret fairness, though it appears incremental in building on existing fairness definitions.
The paper tackles the problem of evaluating fairness in classification algorithms by proposing a framework that learns an underlying 'true' fairness concept from an oracle, enabling the extraction of a metric for individual fairness. The main technical result is a higher fidelity extractor under mild constraints, with implications for interpretability in human arbitration.
It is well understood that classification algorithms, for example, for deciding on loan applications, cannot be evaluated for fairness without taking context into account. We examine what can be learned from a fairness oracle equipped with an underlying understanding of ``true'' fairness. The oracle takes as input a (context, classifier) pair satisfying an arbitrary fairness definition, and accepts or rejects the pair according to whether the classifier satisfies the underlying fairness truth. Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle. Since every ``truly fair'' classifier induces a coarse metric, in which those receiving the same decision are at distance zero from one another and those receiving different decisions are at distance one, this extraction process provides the basis for ensuring a rough form of metric fairness, also known as individual fairness. Our principal technical result is a higher fidelity extractor under a mild technical constraint on the weak oracle's conception of fairness. Our framework permits the scenario in which many classifiers, with differing outcomes, may all be considered fair. Our results have implications for interpretablity -- a highly desired but poorly defined property of classification systems that endeavors to permit a human arbiter to reject classifiers deemed to be ``unfair'' or illegitimately derived.