skip to main content


Title: Blind Pareto Fairness and Subgroup Robustness
Much of the work in the field of group fairness addresses disparities between predefined groups based on protected features such as gender, age, and race, which need to be available at train, and often also at test, time. These approaches are static and retrospective, since algorithms designed to protect groups identified a priori cannot anticipate and protect the needs of different at-risk groups in the future. In this work we analyze the space of solutions for worst-case fairness beyond demographics, and propose Blind Pareto Fairness (BPF), a method that leverages no-regret dynamics to recover a fair minimax classifier that reduces worst-case risk of any potential subgroup of sufficient size, and guarantees that the remaining population receives the best possible level of service. BPF addresses fairness beyond demographics, that is, it does not rely on predefined notions of at-risk groups, neither at train nor at test time. Our experimental results show that the proposed framework improves worst-case risk in multiple standard datasets, while simultaneously providing better levels of service for the remaining population, in comparison to competing methods.  more » « less
Award ID(s):
2031849
NSF-PAR ID:
10231688
Author(s) / Creator(s):
Date Published:
Journal Name:
International Conference Machine Learning
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    This research addresses the global initiative to increase diversity in the engineering work force. The military Veteran student population was identified as one of the most diverse student groups in engineering; however, discontinue and dismissal rates of Veteran students in engineering are significantly higher than traditional engineering students in the United States. These Veteran students hold identifiable traits that are different than traditional engineering students who are under the age of 24 and financially dependent on their parents. While great leaps have been made in engineering student retention, most has focused on these traditional students. This research seeks to fill this gap by specifically addressing the retention of Veteran students using the concept of social responsibility. Social responsibility is generally considered to be acting to benefit society. It is a common ideal promoted in the military (e.g., service before self in the U.S. Air Force fundamental and enduring values). It is also embodied in the engineer’s creed (i.e., engineers using their professional skills to improve human welfare) and revealed by the literature as a major factor that attracts many students from historically underrepresented groups into engineering. Therefore, the objective of this research is to explore the associations between Veteran student retention, social responsibility, and demographics. A survey instrument was developed based on a model for assessing first-year engineering student understanding of social responsibility. The survey was updated to include demographics specific to the Veteran student cohort (e.g., military branch, prior job attributes, and university transfer credits) and questions specifically linking military service and engineering. The survey was piloted, followed by a focus group to clarify survey questions; it was then revised and launched in October 2018 to all students who self-identify as Veterans and all first-year students in the college of engineering at a 4-year land grant institution. Approximately 48% of the Veteran student cohort and 52% of the first-year cohort responded to the survey. This paper will discuss the Veteran and first-year student perceptions of social responsibility in engineering based on results from the instrument. The results of this research will be used to design an intervention, likely in the first-year when most Veteran students discontinue or are dismissed, to increase Veteran retention in engineering programs. 
    more » « less
  2. Data sets and statistics about groups of individuals are increasingly collected and released, feeding many optimization and learning algorithms. In many cases, the released data contain sensitive information whose privacy is strictly regulated. For example, in the U.S., the census data is regulated under Title 13, which requires that no individual be identified from any data released by the Census Bureau. In Europe, data release is regulated according to the General Data Protection Regulation, which addresses the control and transfer of personal data. Differential privacy has emerged as the de-facto standard to protect data privacy. In a nutshell, differentially private algorithms protect an individual’s data by injecting random noise into the output of a computation that involves such data. While this process ensures privacy, it also impacts the quality of data analysis, and, when private data sets are used as inputs to complex machine learning or optimization tasks, they may produce results that are fundamentally different from those obtained on the original data and even rise unintended bias and fairness concerns. In this talk, I will first focus on the challenge of releasing privacy-preserving data sets for complex data analysis tasks. I will introduce the notion of Constrained-based Differential Privacy (C-DP), which allows casting the data release problem to an optimization problem whose goal is to preserve the salient features of the original data. I will review several applications of C-DP in the context of very large hierarchical census data, data streams, energy systems, and in the design of federated data-sharing protocols. Next, I will discuss how errors induced by differential privacy algorithms may propagate within a decision problem causing biases and fairness issues. This is particularly important as privacy-preserving data is often used for critical decision processes, including the allocation of funds and benefits to states and jurisdictions, which ideally should be fair and unbiased. Finally, I will conclude with a roadmap to future work and some open questions. 
    more » « less
  3. 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
  4. Abstract

    Migration is an adaptive life‐history strategy across taxa that helps individuals maximise fitness by obtaining forage and avoiding predation risk. The mechanisms driving migratory changes are poorly understood, and links between migratory behaviour, space use, and demographic consequences are rare.

    Here, we use a nearly 20‐year record of individual‐based monitoring of a large herbivore, elk (Cervus canadensis) to test hypotheses for changing patterns of migration in and adjacent to a large protected area in Banff National Park (BNP), Canada.

    We test whether bottom‐up (forage quality) or top‐down (predation risk) factors explained trends in (i) the proportion of individuals using 5 different migratory tactics, (ii) differences in survival rates of migratory tactics during migration and whilst on summer ranges, (iii) cause‐specific mortality by wolves and grizzly bears, and (iv) population abundance.

    We found dramatic shifts in migration consistent with behavioural plasticity in individual choice of annual migratory routes. Shifts were inconsistent with exposure to the bottom‐up benefits of migration. Instead, exposure to landscape gradients in predation risk caused by exploitation outside the protected area drove migratory shifts. Carnivore exploitation outside the protected area led to higher survival rates for female elk remaining resident or migrating outside the protected area.

    Cause‐specific mortality aligned with exposure to predation risk along migratory routes and summer ranges. Wolf predation risk was higher on migratory routes than summer ranges of montane‐migrant tactics, but wolf predation risk traded‐off with heightened risk from grizzly bears on summer ranges. A novel eastern migrant tactic emerged following a large forest fire that enhanced forage in an area with lower predation risk outside of the protected area.

    The changes in migratory behaviour translated to population abundance, where abundance of the montane‐migratory tactics declined over time. The presence of diverse migratory life histories maintained a higher total population abundance than would have been the case with only one migratory tactic in the population.

    Our study demonstrates the complex ways in which migratory populations change over time through behavioural plasticity and associated demographic consequences because of individuals balancing predation risk and forage trade‐offs.

     
    more » « less
  5. We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring techniques for learning invariant representations from multiple "studies" (or domains), where each study is drawn according to a distribution on domains. The mapping is used at test time to classify instances from a new domain. In many contexts, such as medical forecasting, domain generalization from studies in populous areas (where data are plentiful), to geographically remote populations (for which no training data exist) provides fairness of a different flavor, not anticipated in previous work on algorithmic fairness. We study an adversarial loss function for k domains and precisely characterize its limiting behavior as k grows, formalizing and proving the intuition, backed by experiments, that observing data from a larger number of domains helps. The limiting results are accompanied by non-asymptotic learning-theoretic bounds. Furthermore, we obtain sufficient conditions for good worst-case prediction performance of our algorithm on previously unseen domains. Finally, we decompose our mappings into two components and provide a complete characterization of invariance in terms of this decomposition. To our knowledge, our results provide the first formal guarantees of these kinds for adversarial invariant domain generalization. 
    more » « less