mlsanityData to 7 Oct 2026

Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements

arXiv 1901.04562 ↗First posted 14 Jan 2019cs.LG cs.AI cs.CYcited by 70

Not on the map. Why?

Abstract (arXiv)

As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of machine learning. This research has greatly expanded our understanding of the concerns and challenges in deploying machine learning, but there has been much less work in seeing how the rubber meets the road. In this paper we provide a case-study on the application of fairness in machine learning research to a production classification system, and offer new insights in how to measure and address algorithmic fairness issues. We discuss open questions in implementing equality of opportunity and describe our fairness metric, conditional equality, that takes into account distributional differences. Further, we provide a new approach to improve on the fairness metric during model training and demonstrate its efficacy in improving performance for a real-world product

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 13; 2023: 19; 2024: 8; 2025: 9; 2026: 4.

70 papers.

Sort:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  3. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  4. 2021A Step Toward More Inclusive People Annotations for Fairnesscited by 46
  5. 2023A Survey on Popularity Bias in Recommender Systemscited by 42
  6. 2022Unbiased Supervised Contrastive Learningcited by 40
  7. 2021FARF: A Fair and Adaptive Random Forests Classifiercited by 37
  8. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  9. 2021Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learningcited by 34
  10. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  11. 2021Outlining Traceability: A Principle for Operationalizing Accountability in Computing Systemscited by 26
  12. 2021A Stochastic Optimization Framework for Fair Risk Minimizationcited by 26
38 more
  1. 2021Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Developmentcited by 21
  2. 2022Longitudinal Fairness with Censorshipcited by 21
  3. 2021Technical Challenges for Training Fair Neural Networkscited by 20
  4. 2021Fairness On The Ground: Applying Algorithmic Fairness Approaches to Production Systemscited by 20
  5. 2022A Survey on Fairness for Machine Learning on Graphscited by 20
  6. 2022Efficient Conditionally Invariant Representation Learningcited by 19
  7. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  8. 2023FRAPPE: A Group Fairness Framework for Post-Processing Everythingcited by 16
  9. 2023Fair Decision-making Under Uncertaintycited by 15
  10. 2021Towards Equity and Algorithmic Fairness in Student Grade Predictioncited by 13
  11. 2022FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Datacited by 13
  12. 2022Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animalscited by 11
  13. 2021Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice modelscited by 10
  14. 2022Fairness and Bias in Robot Learningcited by 10
  15. 2024Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimationcited by 10
  16. 2021Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approachcited by 9
  17. 2022Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraintscited by 9
  18. 2023In the Name of Fairness: Assessing the Bias in Clinical Record De-identificationcited by 9
  19. 2024FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficientlycited by 8
  20. 2021Measuring Model Fairness under Noisy Covariates: A Theoretical Perspectivecited by 7
  21. 2023Travel Demand Forecasting: A Fair AI Approachcited by 7
  22. 2023Disentangling and Operationalizing AI Fairness at LinkedIncited by 7
  23. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  24. 2025Evaluating the Promise and Pitfalls of LLMs in Hiring Decisionscited by 7
  25. 2024Fairness without Sensitive Attributes via Knowledge Sharingcited by 6
  26. 2021Machine Learning for Fraud Detection in E-Commerce: A Research Agendacited by 5
  27. 2023Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustmentcited by 5
  28. 2023Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithmscited by 5
  29. 2024On the Inductive Biases of Demographic Parity-based Fair Learning Algorithmscited by 5
  30. 2022Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Talecited by 4
  31. 2023Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraintcited by 4
  32. 2023Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) datacited by 3
  33. 2023Fairness-Enhancing Vehicle Rebalancing in the Ride-hailing Systemcited by 3
  34. 2024Regulation Games for Trustworthy Machine Learningcited by 3
  35. 2024Inducing Group Fairness in Prompt-Based Language Model Decisionscited by 3
  36. 2022Unsupervised Learning of Unbiased Visual Representationscited by 2
  37. 2023On the Within-Group Fairness of Screening Classifierscited by 2
  38. 2023Machine Learning practices and infrastructurescited by 2

50 most cited of 70 All 70 (JSON)