Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJune 2024
Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias
FAccT '24: Proceedings of the 2024 ACM Conference on Fairness, Accountability, and TransparencyPages 2113–2147https://doi.org/10.1145/3630106.3659029Model-induced distribution shifts (MIDS) occur as previous model outputs pollute new model training sets over generations of models. This is known as model collapse in the case of generative models, and performative prediction or unfairness feedback ...
- research-articleJune 2024
Insights From Insurance for Fair Machine Learning
FAccT '24: Proceedings of the 2024 ACM Conference on Fairness, Accountability, and TransparencyPages 407–421https://doi.org/10.1145/3630106.3658914We argue that insurance can act as an analogon for the social situatedness of machine learning systems, hence allowing machine learning scholars to take insights from the rich and interdisciplinary insurance literature. Tracing the interaction of ...
- research-articleMarch 2024
Synthetic Dataset Generation for Fairer Unfairness Research
LAK '24: Proceedings of the 14th Learning Analytics and Knowledge ConferencePages 200–209https://doi.org/10.1145/3636555.3636868Recent research has made strides toward fair machine learning. Relatively few datasets, however, are commonly examined to evaluate these fairness-aware algorithms, and even fewer in education domains, which can lead to a narrow focus on particular types ...
- research-articleAugust 2023
Learning Optimal Fair Decision Trees: Trade-offs Between Interpretability, Fairness, and Accuracy
AIES '23: Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and SocietyPages 181–192https://doi.org/10.1145/3600211.3604664The increasing use of machine learning in high-stakes domains – where people’s livelihoods are impacted – creates an urgent need for interpretable, fair, and highly accurate algorithms. With these needs in mind, we propose a mixed integer optimization (...
- surveyJuly 2023
What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
ACM Computing Surveys (CSUR), Volume 55, Issue 13sArticle No.: 299, Pages 1–37https://doi.org/10.1145/3597199We review and reflect on fairness notions proposed in machine learning literature and make an attempt to draw connections to arguments in moral and political philosophy, especially theories of justice. We survey dynamic fairness inquiries and further ...
-
- research-articleMarch 2024
The measure and mismeasure of fairness
The Journal of Machine Learning Research (JMLR), Volume 24, Issue 1Article No.: 312, Pages 14730–14846The field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last decade, several formal, mathematical definitions of fairness have gained prominence. Here we first assemble and categorize these ...
- research-articleMarch 2024
Interpretable and fair boolean rule sets via column generation
The Journal of Machine Learning Research (JMLR), Volume 24, Issue 1Article No.: 229, Pages 10795–10844This paper considers the learning of Boolean rules in disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy ...
- abstractJuly 2022
What's (Not) Ideal about Fair Machine Learning?
AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and SocietyPage 911https://doi.org/10.1145/3514094.3539543Fair machine learning frameworks are normative models that specify and guide the implementation of non-discrimination principles in machine learning (ML) systems. The dominant methodological approach involves (i) defining a fairness metric, the maximum ...
- research-articleJuly 2022
Strategic Best Response Fairness in Fair Machine Learning
AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and SocietyPage 664https://doi.org/10.1145/3514094.3534194While artificial intelligence (AI) and machine learning (ML) have been increasingly used for decision-making, issues related to discrimination in AI/ML have become prominent. While several fair algorithms are proposed to alleviate these discrimination ...
- research-articleJuly 2022
Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation
AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and SocietyPages 357–368https://doi.org/10.1145/3514094.3534154Credit is an essential component of financial wellbeing in America, and unequal access to it is a large factor in the economic disparities between demographic groups that exist today. Today, machine learning algorithms, sometimes trained on alternative ...
- research-articleJune 2022
Causal Feature Selection for Algorithmic Fairness
SIGMOD '22: Proceedings of the 2022 International Conference on Management of DataPages 276–285https://doi.org/10.1145/3514221.3517909The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high-quality training data, most of the ...
- research-articleJune 2022
“Un”Fair Machine Learning Algorithms
Ensuring fairness in algorithmic decision making is a crucial policy issue. Current legislation ensures fairness by barring algorithm designers from using demographic information in their decision making. As a result, to be legally compliant, the ...
- research-articleMay 2022
EiFFFeL: enforcing fairness in forests by flipping leaves
SAC '22: Proceedings of the 37th ACM/SIGAPP Symposium on Applied ComputingPages 429–436https://doi.org/10.1145/3477314.3507319Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been proposed to address and to make sure ...
- short-paperMarch 2022
Do Gender and Race Matter? Supporting Help-Seeking with Fair Peer Recommenders in an Online Algebra Learning Platform
LAK22: LAK22: 12th International Learning Analytics and Knowledge ConferencePages 432–437https://doi.org/10.1145/3506860.3506869Discussion forums are important for students’ knowledge inquiry in online contexts, with help-seeking being an essential learning strategy in discussion forums. This study aimed to explore innovative methods to build a peer recommender that can provide ...
- research-articleOctober 2021
Everyday Algorithm Auditing: Understanding the Power of Everyday Users in Surfacing Harmful Algorithmic Behaviors
Proceedings of the ACM on Human-Computer Interaction (PACMHCI), Volume 5, Issue CSCW2Article No.: 433, Pages 1–29https://doi.org/10.1145/3479577A growing body of literature has proposed formal approaches to audit algorithmic systems for biased and harmful behaviors. While formal auditing approaches have been greatly impactful, they often suffer major blindspots, with critical issues surfacing ...
- posterJuly 2021
Fairness and Machine Fairness
AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and SocietyPage 446https://doi.org/10.1145/3461702.3462577Prediction-based decisions, which are often made by utilizing the tools of machine learning, influence nearly all facets of modern life. Ethical concerns about this widespread practice have given rise to the field of fair machine learning and a number ...
- research-articleJuly 2021
Minimax Group Fairness: Algorithms and Experiments
AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and SocietyPages 66–76https://doi.org/10.1145/3461702.3462523We consider a recently introduced framework in which fairness is measured by worst-case outcomes across groups, rather than by the more standard differences between group outcomes. In this framework we provide provably convergent oracle-efficient ...
- research-articleJuly 2021
Fair Machine Learning Under Partial Compliance
AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and SocietyPages 55–65https://doi.org/10.1145/3461702.3462521Typically, fair machine learning research focuses on a single decision maker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces with many ...
- short-paperApril 2021
Yet Another Predictive Model? Fair Predictions of Students’ Learning Outcomes in an Online Math Learning Platform
LAK21: LAK21: 11th International Learning Analytics and Knowledge ConferencePages 572–578https://doi.org/10.1145/3448139.3448200To support online learners at a large scale, extensive studies have adopted machine learning (ML) techniques to analyze students’ artifacts and predict their learning outcomes automatically. However, limited attention has been paid to the fairness of ...
- research-articleOctober 2020
Incentives Needed for Low-Cost Fair Lateral Data Reuse
FODS '20: Proceedings of the 2020 ACM-IMS on Foundations of Data Science ConferencePages 71–82https://doi.org/10.1145/3412815.3416890A central goal of algorithmic fairness is to build systems with fairness properties that compose gracefully. A major effort and step towards this goal in data science has been the development offair representations which guarantee demographic parity ...