More Like this

1. Privacy for All: Ensuring Fair and Equitable Privacy Protections

   Ekstrand, Michael D. ; Joshaghani, Rezvan ; Mehrpouyan, Hoda ( January 2018 , 1st Conference on Fairness, Accountability and Transparency)

   null (Ed.)

   In this position paper, we argue for applying recent research on ensuring sociotechnical systems are fair and non-discriminatory to the privacy protections those systems may provide. Privacy literature seldom considers whether a proposed privacy scheme protects all persons uniformly, irrespective of membership in protected classes or particular risk in the face of privacy failure. Just as algorithmic decision-making systems may have discriminatory outcomes even without explicit or deliberate discrimination, so also privacy regimes may disproportionately fail to protect vulnerable members of their target population, resulting in disparate impact with respect to the effectiveness of privacy protections.We propose a research agenda that will illuminate this issue, along with related issues in the intersection of fairness and privacy, and present case studies that show how the outcomes of this research may change existing privacy and fairness research. We believe it is important to ensure that technologies and policies intended to protect the users and subjects of information systems provide such protection in an equitable fashion. 

   more » « less
2. Mobility Equity and Economic Sustainability Using Game Theory

   Chremos, I.V. ; Malikopoulos, A.A. ( May 2023 , 2023 American Control Conference)

   In this paper, we consider a multi-modal mobility system of travelers each with an individual travel budget, and propose a game-theoretic framework to assign each traveler to a “mobility service” (each one representing a different mode of transportation). We are interested in equity and sustainability, thus we maximize the worst-case revenue of the mobility system while ensuring “mobility equity,” which we define it in terms of accessibility. In the proposed framework, we ensure that all travelers are truthful and voluntarily participate under informational asymmetry, and the solution respects the individual budget of each traveler. Each traveler may seek to travel using multiple services (e.g., car, bus, train, bike). The services are capacitated and can serve up to a fixed number of travelers at any instant of time. Thus, our problem falls under the category of many-to-one assignment problems, where the goal is to find the conditions that guarantee the stability of assignments. We formulate a linear program of maximizing worst-case revenue under the constraints of mobility equity, and we fully characterize the optimal solution. 

   more » « less
3. Fairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Results

   https://doi.org/10.1609/aaai.v37i10.26397  

   Jo, Nathanael ; Tang, Bill ; Dullerud, Kathryn ; Aghaei, Sina ; Rice, Eric ; Vayanos, Phebe ( June 2023 , Proceedings of the AAAI Conference on Artificial Intelligence)

   We study critical systems that allocate scarce resources to satisfy basic needs, such as homeless services that provide housing. These systems often support communities disproportionately affected by systemic racial, gender, or other injustices, so it is crucial to design these systems with fairness considerations in mind. To address this problem, we propose a framework for evaluating fairness in contextual resource allocation systems that is inspired by fairness metrics in machine learning. This framework can be applied to evaluate the fairness properties of a historical policy, as well as to impose constraints in the design of new (counterfactual) allocation policies. Our work culminates with a set of incompatibility results that investigate the interplay between the different fairness metrics we propose. Notably, we demonstrate that: 1) fairness in allocation and fairness in outcomes are usually incompatible; 2) policies that prioritize based on a vulnerability score will usually result in unequal outcomes across groups, even if the score is perfectly calibrated; 3) policies using contextual information beyond what is needed to characterize baseline risk and treatment effects can be fairer in their outcomes than those using just baseline risk and treatment effects; and 4) policies using group status in addition to baseline risk and treatment effects are as fair as possible given all available information. Our framework can help guide the discussion among stakeholders in deciding which fairness metrics to impose when allocating scarce resources. 

   more » « less
4. Fair and Robust Classification Under Sample Selection Bias

   https://doi.org/10.1145/3459637.3482104  

   Du, Wei ; Wu, Xintao ( October 2021 , 30th ACM International Conference on Information & Knowledge Management)

   To address the sample selection bias between the training and test data, previous research works focus on reweighing biased training data to match the test data and then building classification models on there weighed raining data. However, how to achieve fairness in the built classification models is under-explored. In this paper, we propose a framework for robust and fair learning under sample selection bias. Our framework adopts there weighing estimation approach for bias correction and the minimax robust estimation approach for achieving robustness on prediction accuracy. Moreover, during the minimax optimization, the fairness is achieved under the worst case, which guarantees the model’s fairness on test data. We further develop two algorithms to handle sample selection bias when test data is both available and unavailable. 

   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