mlsanityData to 7 Oct 2026

A Catalog of Fairness-Aware Practices in Machine Learning Engineering

arXiv 2408.16683 ↗First posted 29 Aug 2024cs.SE cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Machine learning's widespread adoption in decision-making processes raises concerns about fairness, particularly regarding the treatment of sensitive features and potential discrimination against minorities. The software engineering community has responded by developing fairness-oriented metrics, empirical studies, and approaches. However, there remains a gap in understanding and categorizing practices for engineering fairness throughout the machine learning lifecycle. This paper presents a novel catalog of practices for addressing fairness in machine learning derived from a systematic mapping study. The study identifies and categorizes 28 practices from existing literature, mapping them onto different stages of the machine learning lifecycle. From this catalog, the authors extract actionable items and implications for both researchers and practitioners in software engineering. This work aims to provide a comprehensive resource for integrating fairness considerations into the development and deployment of machine learning systems, enhancing their reliability, accountability, and credibility.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 59 of its 182 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

59 of 182 references.

References · 59

  1. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  2. 2017Fairness in Criminal Justice Risk Assessments: The State of the Artcited by 315
  3. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
  4. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
  5. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  6. 2018Fairness of Exposure in Rankingscited by 189
  7. 2023Gender bias and stereotypes in Large Language Modelscited by 185
  8. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  9. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  10. 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
  11. 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 137
  12. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
38 more
  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  3. 2017Fairness Testing: Testing Software for Discriminationcited by 123
  4. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  5. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  6. 2018Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobservedcited by 94
  7. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
  8. 2018Automated Directed Fairness Testingcited by 77
  9. 2018Bias Mitigation Post-processing for Individual and Group Fairnesscited by 72
  10. 2020Lagrangian Duality for Constrained Deep Learningcited by 72
  11. 2021Software Engineering for AI-Based Systems: A Surveycited by 68
  12. 2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
  13. 2020How do Data Science Workers Collaborate? Roles, Workflows, and Toolscited by 64
  14. 2021Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Supportcited by 61
  15. 2022Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluationcited by 59
  16. 2022Algorithmic Fairness Datasets: the Story so Farcited by 51
  17. 2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
  18. 2020Exacerbating Algorithmic Bias through Fairness Attackscited by 47
  19. 2020FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learningcited by 44
  20. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  21. 2018Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Datacited by 39
  22. 2020FAE: A Fairness-Aware Ensemble Frameworkcited by 34
  23. 2021Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Researchcited by 34
  24. 2020Adoption and Effects of Software Engineering Best Practices in Machine Learningcited by 33
  25. 2022Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkitscited by 33
  26. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  27. 2021Elliot: a Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluationcited by 28
  28. 2022Dbias: Detecting biases and ensuring Fairness in news articlescited by 28
  29. 2020LiFT: A Scalable Framework for Measuring Fairness in ML Applicationscited by 22
  30. 2020Fairness in Semi-supervised Learning: Unlabeled Data Help to Reduce Discriminationcited by 22
  31. 2019Requirements Engineering Challenges in Building AI-Based Complex Systemscited by 21
  32. 2021BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systemscited by 20
  33. 2019Software Engineering for Fairness: A Case Study with Hyperparameter Optimizationcited by 18
  34. 2021OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learningcited by 18
  35. 2021Maxmin-Fair Ranking: Individual Fairness under Group-Fairness Constraintscited by 18
  36. 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
  37. 2021Data synthesis and adversarial networks: A review and meta-analysis in cancer imagingcited by 15
  38. 2022AI Ethics Issues in Real World: Evidence from AI Incident Databasecited by 14

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024From Expectation to Habit: Why Do Software Practitioners Adopt Fairness Toolkits?cited by 1
  2. 2024Data Preparation for Fairness-Performance Trade-Offs: A Practitioner-Friendly Alternative?cited by 0
  3. 2025A Gray Literature Study on Fairness Requirements in AI-enabled Software Engineeringcited by 0
  4. 2026Intersectional Fairness in Large Language Modelscited by 0