mlsanityData to 7 Oct 2026

When Fair Ranking Meets Uncertain Inference

arXiv 2105.02091 ↗First posted 5 May 2021cs.IR cs.CY cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Existing fair ranking systems, especially those designed to be demographically fair, assume that accurate demographic information about individuals is available to the ranking algorithm. In practice, however, this assumption may not hold -- in real-world contexts like ranking job applicants or credit seekers, social and legal barriers may prevent algorithm operators from collecting peoples' demographic information. In these cases, algorithm operators may attempt to infer peoples' demographics and then supply these inferences as inputs to the ranking algorithm. In this study, we investigate how uncertainty and errors in demographic inference impact the fairness offered by fair ranking algorithms. Using simulations and three case studies with real datasets, we show how demographic inferences drawn from real systems can lead to unfair rankings. Our results suggest that developers should not use inferred demographic data as input to fair ranking algorithms, unless the inferences are extremely accurate.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 47 of its 87 references that are in the map. First posted on arXiv 5 May 2021.

Builds on

47 of 87 references.

References · 47

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  7. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  8. 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
  9. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  10. 2018Fairness of Exposure in Rankingscited by 189
  11. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  12. 2017A Convex Framework for Fair Regressioncited by 147
35 more
  1. 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
  2. 2017Fair Inference On Outcomescited by 143
  3. 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 137
  4. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  5. 2018An Intersectional Definition of Fairnesscited by 126
  6. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  7. 2019Towards a Critical Race Methodology in Algorithmic Fairnesscited by 124
  8. 2019Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learningcited by 116
  9. 2017FA*IR: A Fair Top-k Ranking Algorithmcited by 113
  10. 2018Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobservedcited by 94
  11. 2016Fairness in Reinforcement Learningcited by 93
  12. 2018Understanding the Origins of Bias in Word Embeddingscited by 90
  13. 2016Measuring Fairness in Ranked Outputscited by 81
  14. 2017Ranking with Fairness Constraintscited by 78
  15. 2020Controlling Fairness and Bias in Dynamic Learning-to-Rankcited by 67
  16. 2019Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniquescited by 65
  17. 2019Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?cited by 64
  18. 2020"What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairnesscited by 56
  19. 2020Evaluating Stochastic Rankings with Expected Exposurecited by 53
  20. 2018Causal Reasoning for Algorithmic Fairnesscited by 51
  21. 2021Characterizing Intersectional Group Fairness with Worst-Case Comparisonscited by 42
  22. 2020What's Sex Got To Do With Fair Machine Learning?cited by 37
  23. 2020Mitigating Bias in Set Selection with Noisy Protected Attributescited by 29
  24. 2019Stable and Fair Classificationcited by 25
  25. 2018Predicting Race and Ethnicity From the Sequence of Characters in a Namecited by 24
  26. 2019Quantifying the Impact of User Attention on Fair Group Representation in Ranked Listscited by 24
  27. 2019Awareness in Practice: Tensions in Access to Sensitive Attribute Data for Antidiscriminationcited by 23
  28. 2019FairSearch: A Tool For Fairness in Ranked Search Resultscited by 22
  29. 2019The Diversity-Innovation Paradox in Sciencecited by 21
  30. 2017Quantifying Search Bias: Investigating Sources of Bias for Political Searches in Social Mediacited by 18
  31. 2019Implicit Diversity in Image Summarizationcited by 18
  32. 2017Nationality Classification Using Name Embeddingscited by 10
  33. 2020Comparing Fair Ranking Metricscited by 8
  34. 2020Fair Classification with Noisy Protected Attributes: A Framework with Provable Guaranteescited by 5
  35. 2019Public Sphere 2.0: Targeted Commenting in Online News Mediacited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

22 papers.

Sort:

  1. 2022Fairness in Recommender Systems: Research Landscape and Future Directionscited by 30
  2. 2021Fairness in Ranking under Uncertaintycited by 27
  3. 2022Fair ranking: a critical review, challenges, and future directionscited by 21
  4. 2022Fair Ranking with Noisy Protected Attributescited by 17
  5. 2022Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harmscited by 10
  6. 2021Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approachcited by 9
  7. 2023China and the U.S. produce more impactful AI research when collaborating togethercited by 6
  8. 2023FRAMM: Fair Ranking with Missing Modalities for Clinical Trial Site Selectioncited by 6
  9. 2023When Fair Classification Meets Noisy Protected Attributescited by 6
  10. 2024Measuring and Addressing Indexical Bias in Information Retrievalcited by 6
  11. 2022Subverting Fair Image Search with Generative Adversarial Perturbationscited by 5
  12. 2023Fairness in Matching under Uncertaintycited by 5
10 more
  1. 2024Measuring Bias in a Ranked List using Term-based Representationscited by 4
  2. 2024Addressing Discretization-Induced Bias in Demographic Predictioncited by 4
  3. 2023The Role of Relevance in Fair Rankingcited by 3
  4. 2025Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairnesscited by 3
  5. 2022Properties of Group Fairness Metrics for Rankingscited by 2
  6. 2023Sampling Individually-Fair Rankings that are Always Group Faircited by 2
  7. 2024Hidden or Inferred: Fair Learning-To-Rank with Unknown Demographicscited by 2
  8. 2021Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rankcited by 1
  9. 2025A Tutorial On Intersectionality in Fair Rankingscited by 0
  10. 2026Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Studycited by 0