More Like this

1. FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

   https://doi.org/10.1007/978-3-030-58610-2_22  

   Lokhande, Vishnu S; Akash, Aditya Kumar; Ravi, Sathya N; Singh, Vikas (January 2020, European Conference on Computer Vision)

   null (Ed.)

   Algorithmic decision making based on computer vision and machine learning methods continues to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to legitimate concerns. There is agreement that because of biases in the datasets we present to the models, a fairness-oblivious training will lead to unfair models. An interesting topic is the study of mechanisms via which the de novo design or training of the model can be informed by fairness measures. Here, we study strategies to impose fairness concurrently while training the model. While many fairness based approaches in vision rely on training adversarial modules together with the primary classification/regression task, in an effort to remove the influence of the protected attribute or variable, we show how ideas based on well-known optimization concepts can provide a simpler alternative. In our proposal, imposing fairness just requires specifying the protected attribute and utilizing our routine. We provide a detailed technical analysis and present experiments demonstrating that various fairness measures can be reliably imposed on a number of training tasks in vision in a manner that is interpretable. 

   more » « less
2. A Psychometric Framework for Evaluating Fairness in Algorithmic Decision Making: Differential Algorithmic Functioning

   https://doi.org/10.3102/10769986231171711  

   Suk, Youmi; Han, Kyung_T (May 2023, Journal of Educational and Behavioral Statistics)

   As algorithmic decision making is increasingly deployed in every walk of life, many researchers have raised concerns about fairness-related bias from such algorithms. But there is little research on harnessing psychometric methods to uncover potential discriminatory bias inside decision-making algorithms. The main goal of this article is to propose a new framework for algorithmic fairness based on differential item functioning (DIF), which has been commonly used to measure item fairness in psychometrics. Our fairness notion, which we call differential algorithmic functioning (DAF), is defined based on three pieces of information: a decision variable, a “fair” variable, and a protected variable such as race or gender. Under the DAF framework, an algorithm can exhibit uniform DAF, nonuniform DAF, or neither (i.e., non-DAF). For detecting DAF, we provide modifications of well-established DIF methods: Mantel–Haenszel test, logistic regression, and residual-based DIF. We demonstrate our framework through a real dataset concerning decision-making algorithms for grade retention in K–12 education in the United States. 

   more » « less
3. 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
4. Wasserstein Robust Classification with Fairness Constraints

   https://doi.org/10.1287/msom.2022.0230  

   Wang, Yijie; Nguyen, Viet Anh; Hanasusanto, Grani A (July 2024, Manufacturing & Service Operations Management)

   Problem definition: Data analytics models and machine learning algorithms are increasingly deployed to support consequential decision-making processes, from deciding which applicants will receive job offers and loans to university enrollments and medical interventions. However, recent studies show these models may unintentionally amplify human bias and yield significant unfavorable decisions to specific groups. Methodology/results: We propose a distributionally robust classification model with a fairness constraint that encourages the classifier to be fair in the equality of opportunity criterion. We use a type-[Formula: see text] Wasserstein ambiguity set centered at the empirical distribution to represent distributional uncertainty and derive a conservative reformulation for the worst-case equal opportunity unfairness measure. We show that the model is equivalent to a mixed binary conic optimization problem, which standard off-the-shelf solvers can solve. We propose a convex, hinge-loss-based model for large problem instances whose reformulation does not incur binary variables to improve scalability. Moreover, we also consider the distributionally robust learning problem with a generic ground transportation cost to hedge against the label and sensitive attribute uncertainties. We numerically examine the performance of our proposed models on five real-world data sets related to individual analysis. Compared with the state-of-the-art methods, our proposed approaches significantly improve fairness with negligible loss of predictive accuracy in the testing data set. Managerial implications: Our paper raises awareness that bias may arise when predictive models are used in service and operations. It generally comes from human bias, for example, imbalanced data collection or low sample sizes, and is further amplified by algorithms. Incorporating fairness constraints and the distributionally robust optimization (DRO) scheme is a powerful way to alleviate algorithmic biases. Funding: This work was supported by the National Science Foundation [Grants 2342505 and 2343869] and the Chinese University of Hong Kong [Grant 4055191]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2022.0230 . 

   more » « less
5. It’s All Relative: Examining Student Ethical Decision Making in a Narrative Game-Based Ethical Intervention

   https://doi.org/10.1109/FIE56618.2022.9962629  

   Burkey, Daniel D.; Cimino, Richard T.; Young, Michael F.; Dahm, Kevin D.; Streiner, Scott C. (October 2022, 2022 IEEE Frontiers in Education Conference (FIE))

   This Innovative Practice Full Paper presents a novel, narrative, game-based approach to introducing first-year engineering students to concepts in ethical decision making. Approximately 250 first-year engineering students at the University of Connecticut played through our adventure, titled Mars: An Ethical Expedition, by voting weekly as a class on a presented dilemma. Literature shows that case studies still dominate learning sciences research on engineering ethical education, and that novel, active learning-based techniques, such as games, are infrequently used but can have a positive impact on both student engagement and learning. In this work, we suggest that games are a form of situated (context-based) learning, where the game setting provides learners with an authentic but safe space in which to explore engineering ethical choices and their consequences. As games normalize learning through failure, they present a unique opportunity for students to explore ethical decision making in a non-judgmental, playful, and safe way.We explored the situated nature of ethical decision making through a qualitative deconstruction of the weekly scenarios that students engaged with over the course of the twelve-week narrative. To assess their ethical reasoning, students took the Engineering Ethics Reasoning Instrument (EERI), a quantitative engineering ethics reasoning survey, at the beginning and end of the semester. The EERI scenarios were deconstructed to reveal their core ethical dilemmas, and then common elements between the EERI and our Mars adventure were compared to determine how students responded to similar ethical dilemmas presented in each context.We noted that students' responses to the ethical decisions in the Mars adventure scenarios were sometimes substantially different both from their response to the EERI scenario as well as from other decisions they made within the context of the game, despite the core ethical dilemma being the same. This suggests that they make ethical decisions in some situations that differ from a presumed abstract understanding of post-conventional moral reasoning. This has implications for how ethical reasoning can be taught and scaffolded in educational settings. 

   more » « less