The Frontiers of Fairness in Machine Learning

By Alexandra Chouldechova, Aaron Roth. 2018

439 citations recorded by the source corpus.

The last few years have seen an explosion of academic and popular interest in algorithmic fairness. Despite this interest and the volume and velocity of work that has been produced recently, the fundamental science of fairness in machine learning is still in a nascent state. In March 2018, we convened a group of experts as part of a CCC visioning workshop to assess the state of the field, and distill the most promising research directions going forward. This report summarizes the findings of that workshop. Along the way, it surveys recent theoretical work in the field and points towards promising directions for research.

Subfields: Artificial Intelligence, Computer Science Applications, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

Measurement and Fairness (2019, background): “Again, while this argument is largely held at the operationalization level [13, 18, 36, 12], this disagreement lives at the construct level.”
On The Impact of Machine Learning Randomness on Group Fairness (2023, background): “[15] Alexandra Chouldechova and Aaron Roth.”
Mitigating Gender Bias in Natural Language Processing: Literature Review (2019, background): “However, we recognize that different applications may require different metrics and there are trade-offs between different notions of biases (Barocas et al., 2018; Chouldechova and Roth, 2018).”
A Survey on Bias and Fairness in Machine Learning (2019, background): “phenomenon, which is a situation where the trained machine learning model informs decisions that then affect the data collected for future iterations of the training process [33], these definitions are intertwined, and we need a categorization which closely models this situation.”
Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “But there can be regions of the covariates where no data exists to fit a model; for there may be values of a covariate for which no defendants were ever released and hence the outcome in that region is unobserved [15].”
Statistical Equity: A Fairness Classification Objective (2020, background): “An important and major concern in the fairness community is the feedback loop phenomenon [Chouldechova and Roth, 2018].”
Scalable Fair Clustering (2019, background): “See e.g., the survey by Chouldechova and Roth (2018) for an overview.”
Learning Fair Rule Lists (2019, background): “We refer the interested reader to the following surveys [6, 14, 50, 58] for a detailed overview of these notions.”
Algorithmic Fairness (2020, background): “In contrast to other recent surveys in this field [37, 57], our paper proposes a comprehensive and up-to-date overview of the field, ranging from definitions and measures of fairness to state-of-the-art fairness-enhancing mechanisms.”
Toward Annotator Group Bias in Crowdsourcing (2021, neutral): “For example, if we train a model on data that contain labels from two populations - a majority and a minority population - minimizing overall error will ﬁt only the majority population ignoring the minority (Chouldechova and Roth, 2018).”
Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies (2023, methodology): “To combat bias, this paper has highlighted strategies such as robust data augmentation, the application of counterfactual fairness, and the imperative for diverse, representative datasets alongside unbiased data collection methods [49–51].”
Algorithmic Fairness: Choices, Assumptions, and Definitions (2021, background): “That is, they are evaluated in a batch as opposed to serially and so do not consider potentially important temporal dynamics (Chouldechova & Roth 2018).”
A Geometric Solution to Fair Representations (2020, background): “The emerging field of AI fairness has suggested ways to mitigate harmful model biases [6, 7, 11], e.”
Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach (2019, background): “, reweighed [3]) to maximize fairness.”
The Implicit Fairness Criterion of Unconstrained Learning (2018, background): “For a more complete treatment of algorithmic fairness literature, the reader is referred to Barocas et al. (2018); Chouldechova and Roth (2018); Corbett-Davies and Goel (2018).”
Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare (2022, background): “These challenges have spurred research to design performance metrics that maintain or even promote algorithmic fairness and are resistant to the creation of deleterious feedback loops 74 – 76 .”