As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as bias towards gender, ethnicity, and/or people with disabilities. There is significant literature on approaches to mitigate bias and promote fairness, yet the area is complex and hard to penetrate for newcomers to the domain. This article seeks to provide an overview of the different schools of thought and approaches to mitigating (social) biases and increase fairness in the Machine Learning literature. It organises approaches into the widely accepted framework of pre-processing, in-processing, and post-processing methods, subcategorizing into a further 11 method areas. Although much of the literature emphasizes binary classification, a discussion of fairness in regression, recommender systems, unsupervised learning, and natural language processing is also provided along with a selection of currently available open source libraries. The article concludes by summarising open challenges articulated as four dilemmas for fairness research.

pdf/fairness-in-machine-learning-a-survey-38pompjtwz.pdf

Fairness in Machine Learning: A Survey.

We 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 consider the long-term impact induced by current prediction and decision. We present a flowchart that encompasses implicit assumptions and expected outcomes of different fairness inquiries on the data generating process, the predicted outcome, and the induced impact, respectively. We demonstrate the importance of matching the mission (what kind of fairness to enforce) and the means (which appropriate fairness spectrum to analyze) to fulfill the intended purpose.

/pdf/what-is-and-how-to-for-fairness-in-machine-learning-a-survey-2wqv6h6g.pdf

What-Is and How-To for Fairness in Machine Learning: A Survey, Reflection, and Perspective

Integration of Constraint Programming, Artificial Intelligence, and Operations Research: 19th International Conference, CPAIOR 2022, Los Angeles, CA, USA, June 20-23, 2022, Proceedings

The Less Discriminatory Alternative is a key provision of the disparate impact doctrine in the United States. In fair lending, this provision mandates that lenders must adopt models that reduce discrimination when they do not compromise their business interests. In this paper, we develop practical methods to audit for less discriminatory alternatives. Our approach is designed to verify the existence of less discriminatory machine learning models – by returning an alternative model that can reduce discrimination without compromising performance (discovery) or by certifying that an alternative model does not exist (refutation). We develop a method to fit the least discriminatory linear classification model in a specific lending task – by minimizing an exact measure of disparity (e.g., the maximum gap in group FNR) and enforcing hard performance constraints for business necessity (e.g., on FNR and FPR). We apply our method to study the prevalence of less discriminatory alternatives on real-world datasets from consumer finance applications. Our results highlight how models may inadvertently lead to unnecessary discrimination across common deployment regimes, and demonstrate how our approach can support lenders, regulators, and plaintiffs by reliably detecting less discriminatory alternatives in such instances.

Operationalizing the Search for Less Discriminatory Alternatives in Fair Lending

This article focuses on the social choice problem in which decisions are based on the utility of multiple stakeholder types. The sum of these utilities – Utilitarian welfare - is one of the most important objectives in solving the social choice problem. While it is the most efficient solution, maximizing Utilitarian welfare may lead to unfair outcomes. However, Encouraging a Utilitarian decision-maker to adopt a fair decision is challenging due to the associated efficiency loss. This article takes a novel perspective by motivating a Utilitarian decision-maker to make fair decisions from an uncertainty-averse standpoint. We study the problem where the proportions of stakeholder types are uncertain and propose a distributionally robust optimization (DRO) model that maximizes the worst-case Utilitarian welfare over an ϕ-divergence-based uncertainty set. We provide three aspects of the relationship between fairness and the uncertain-averse Utilitarian welfare maximization. First, we establish that the worst-case Utilitarian welfare adheres to all five axioms of unfairness-averse cardinal welfare functions with two stakeholder types and satisfies four of these when this number exceeds two. Second, we demonstrate that with the maximal extent of uncertainty aversion, the DRO model identifies the Egalitarian welfare maximizer, which prioritizes fairness. Further, given serveral conventional assumptions, the proposed model selects the Nash welfare maximizer, an objective trade-off between efficiency and fairness, with moderate levels of uncertainty aversion. Lastly, we present numerical studies of two specific instances of the social choice problem – resource allocation and facility location – to show that, as uncertainty aversion increases, our model increasingly emphasizes fairness.

EXPRESS: Fairness as a Robust Utilitarianism

Fairness and interpretability are fundamental requirements for the development of responsible machine learning. However, learning optimal interpretable models under fairness constraints has been identified as a major challenge. In this paper, we investigate and improve on a state-of-the-art exact learning algorithm, called CORELS, which learns rule lists that are certifiably optimal in terms of accuracy and sparsity. Statistical fairness metrics have been integrated incrementally into CORELS in the literature. This paper demonstrates the limitations of such an approach for exploring the search space efficiently before proposing an Integer Linear Programming method, leveraging accuracy, sparsity and fairness jointly for better pruning. Our thorough experiments show clear benefits of our approach regarding the exploration of the search space. 

/pdf/leveraging-integer-linear-programming-to-learn-optimal-fair-3dkqh25r.pdf

Leveraging Integer Linear Programming to Learn Optimal Fair Rule Lists

Unwanted bias is a major concern in machine learning, raising in particular significant ethical issues when machine learning models are deployed within high-stakes decision systems. A common solution to mitigate it is to integrate and optimize a statistical fairness metric along with accuracy during the training phase. However, one of the main remaining challenges is that current approaches usually generalize poorly in terms of fairness on unseen data. We address this issue by proposing a new robustness framework for statistical fairness in machine learning. The proposed approach is inspired by the domain of distributionally robust optimization and works in ensuring fairness over a variety of samplings of the training set. Our approach can be used to quantify the robustness of fairness but also to improve it when training a model. We empirically evaluate the proposed method and show that it effectively improves fairness generalization. In addition, we propose a simple yet powerful heuristic application of our framework that can be integrated into a wide range of existing fair classification techniques to enhance fairness generalization. Our extensive empirical study using two existing fair classification methods demonstrates the efficiency and scalability of the proposed heuristic approach. 

/pdf/improving-fairness-generalization-through-a-sample-robust-29xsw2fa.pdf

Improving fairness generalization through a sample-robust optimization method

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Mohamed

Author Tools

Chat about Author

Papers

Leveraging Integer Linear Programming to Learn Optimal Fair Rule Lists

Improving fairness generalization through a sample-robust optimization method