More Like this

1. Fairness Under Composition

   Dwork, C; Ilvento, C (January 2019, 10th Innovations in Theoretical Computer Science Conference (ITCS 2019))

   Blum, A (Ed.)

   Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law. Much of the literature considers the case of a single classifier (or scoring function) used once, in isolation. In this work, we initiate the study of the fairness properties of systems composed of algorithms that are fair in isolation; that is, we study fairness under composition. We identify pitfalls of naïve composition and give general constructions for fair composition, demonstrating both that classifiers that are fair in isolation do not necessarily compose into fair systems and also that seemingly unfair components may be carefully combined to construct fair systems. We focus primarily on the individual fairness setting proposed in [Dwork, Hardt, Pitassi, Reingold, Zemel, 2011], but also extend our results to a large class of group fairness definitions popular in the recent literature, exhibiting several cases in which group fairness definitions give misleading signals under composition. 

   more » « less
2. Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data

   https://doi.org/10.1145/3351095.3372839  

   Slack, Dyla; Friedler, Sorelle A.; Givental, Emile (January 2020, Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency)

   Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be quickly fine-tuned to specific tasks from only a few number of sample instances while balancing fairness and accuracy. We demonstrate experimentally the individual utility of each model using relevant baselines and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair. 

   more » « less
3. Abstracting Fairness: Oracles, Metrics, and Interpretability

   Dwork, C; Ilvento, C; Rothblum, G; Sur, P (January 2020, Proceedings of the 1st Symposium on Foundations of Responsible Computing (FORC 2020))

   Roth, A (Ed.)

   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. 

   more » « less
4. Metric-Fair Classifier Derandomization

   Wu, Jimmy; Chen, Yatong; Liu, Yang (January 2022, International Conference on Machine Learning (ICML))

   We study the problem of classifier derandomization in machine learning: given a stochastic binary classifier f:X→[0,1], sample a deterministic classifier f̂ :X→{0,1} that approximates the output of f in aggregate over any data distribution. Recent work revealed how to efficiently derandomize a stochastic classifier with strong output approximation guarantees, but at the cost of individual fairness -- that is, if f treated similar inputs similarly, f̂ did not. In this paper, we initiate a systematic study of classifier derandomization with metric fairness guarantees. We show that the prior derandomization approach is almost maximally metric-unfair, and that a simple ``random threshold'' derandomization achieves optimal fairness preservation but with weaker output approximation. We then devise a derandomization procedure that provides an appealing tradeoff between these two: if f is α-metric fair according to a metric d with a locality-sensitive hash (LSH) family, then our derandomized f̂ is, with high probability, O(α)-metric fair and a close approximation of f. We also prove generic results applicable to all (fair and unfair) classifier derandomization procedures, including a bias-variance decomposition and reductions between various notions of metric fairness. 

   more » « less
5. Residual Unfairness in Fair Machine Learning from Prejudiced Data

   Kallus, Nathan; Zhou, Angela (January 2018, Proceedings of the 35th International Conference on Machine Learning)

   Recent work in fairness in machine learning has proposed adjusting for fairness by equalizing accuracy metrics across groups and has also studied how datasets affected by historical prejudices may lead to unfair decision policies. We connect these lines of work and study the residual unfairness that arises when a fairness-adjusted predictor is not actually fair on the target population due to systematic censoring of training data by existing biased policies. This scenario is particularly common in the same applications where fairness is a concern. We characterize theoretically the impact of such censoring on standard fairness metrics for binary classifiers and provide criteria for when residual unfairness may or may not appear. We prove that, under certain conditions, fairness-adjusted classifiers will in fact induce residual unfairness that perpetuates the same injustices, against the same groups, that biased the data to begin with, thus showing that even state-of-the-art fair machine learning can have a "bias in, bias out" property. When certain benchmark data is available, we show how sample reweighting can estimate and adjust fairness metrics while accounting for censoring. We use this to study the case of Stop, Question, and Frisk (SQF) and demonstrate that attempting to adjust for fairness perpetuates the same injustices that the policy is infamous for. 

   more » « less