More Like this

1. Popularizing Fairness: Group Fairness and Individual Welfare

   https://doi.org/10.1609/aaai.v37i6.25910  

   Estornell, Andrew; Das, Sanmay; Juba, Brendan; Vorobeychik, Yevgeniy (June 2023, Proceedings of the AAAI Conference on Artificial Intelligence)

   Group-fair learning methods typically seek to ensure that some measure of prediction efficacy for (often historically) disadvantaged minority groups is comparable to that for the majority of the population. When a principal seeks to adopt a group-fair approach to replace another, the principal may face opposition from those who feel they may be harmed by the switch, and this, in turn, may deter adoption. We propose that a potential mitigation to this concern is to ensure that a group-fair model is also popular, in the sense that, for a majority of the target population, it yields a preferred distribution over outcomes compared with the conventional model. In this paper, we show that state of the art fair learning approaches are often unpopular in this sense. We propose several efficient algorithms for postprocessing an existing group-fair learning scheme to improve its popularity while retaining fairness. Through extensive experiments, we demonstrate that the proposed postprocessing approaches are highly effective in practice. 

   more » « less
2. Popularizing Fairness: Group Fairness and Individual Welfare

   Estornell, Andrew; Das, Sanmay; Juba, Brendan; Vorobeychik, Yevgeniy (January 2023, Proceedings of the AAAI Conference on Artificial Intelligence)
3. Interventional Fairness: Causal Database Repair for Algorithmic Fairness

   https://doi.org/10.1145/3299869.3319901  

   Salimi, Babak; Rodriguez, Luke; Howe, Bill; Suciu, Dan (January 2019, SIGMOD)
4. Interventional Fairness: Causal Database Repair for Algorithmic Fairness

   Salimi, Babak; Rodriguez, Luke; Howe, Bill; Suciu, Dan (April 2019, SIGMOD)

   Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing treatments of fairness rely on statistical correlations that can be fooled by statistical anomalies, such as Simpson's paradox. Proposals for causality-based definitions of fairness can correctly model some of these situations, but they require specification of the underlying causal models. In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables as opposed to a complete causal model. We show that these conditions correctly capture subtle fairness violations. We then use these conditions as the basis for database repair algorithms that provide provable fairness guarantees about classifiers trained on their training labels. We evaluate our algorithms on real data, demonstrating improvement over the state of the art on multiple fairness metrics proposed in the literature while retaining high utility. 

   more » « less
5. Software fairness

   https://doi.org/10.1145/3236024.3264838  

   Brun, Yuriy; Meliou, Alexandra (January 2018, Proceedings of the New Ideas and Emerging Results Track at the 26th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE))

   A goal of software engineering research is advancing software quality and the success of the software engineering process. However, while recent studies have demonstrated a new kind of defect in software related to its ability to operate in fair and unbiased manner, software engineering has not yet wholeheartedly tackled these new kinds of defects, thus leaving software vulnerable. This paper outlines a vision for how software engineering research can help reduce fairness defects and represents a call to action by the software engineering research community to reify that vision. Modern software is riddled with examples of biased behavior, from automated translation injecting gender stereotypes, to vision systems failing to see faces of certain races, to the US criminal justice system relying on biased computational assessments of crime recidivism. While systems may learn bias from biased data, bias can also emerge from ambiguous or incomplete requirement specification, poor design, implementation bugs, and unintended component interactions. We argue that software fairness is analogous to software quality, and that numerous software engineering challenges in the areas of requirements, specification, design, testing, and verification need to be tackled to solve this problem. 

   more » « less