mlsanityData to 7 Oct 2026

Proxy Non-Discrimination in Data-Driven Systems

arXiv 1707.08120 ↗First posted 25 Jul 2017cs.CY cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Machine learnt systems inherit biases against protected classes, historically disparaged groups, from training data. Usually, these biases are not explicit, they rely on subtle correlations discovered by training algorithms, and are therefore difficult to detect. We formalize proxy discrimination in data-driven systems, a class of properties indicative of bias, as the presence of protected class correlates that have causal influence on the system's output. We evaluate an implementation on a corpus of social datasets, demonstrating how to validate systems against these properties and to repair violations where they occur.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 2; 2023: 1; 2024: 2; 2025: 1; 2026: 2.

13 papers.

Sort:

  1. 2021A survey on datasets for fairness-aware machine learningcited by 157
  2. 2023Evaluating and Mitigating Discrimination in Language Model Decisionscited by 117
  3. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  4. 2021Can Active Learning Preemptively Mitigate Fairness Issues?cited by 15
  5. 2021Equity and Artificial Intelligence in Education: Will "AIEd" Amplify or Alleviate Inequities in Education?cited by 9
  6. 2022What is Proxy Discrimination?cited by 7
  7. 2024Fairness-Aware Meta-Learning via Nash Bargainingcited by 6
  8. 2024Fairness without Sensitive Attributes via Knowledge Sharingcited by 6
  9. 2021Hidden Technical Debts for Fair Machine Learning in Financial Servicescited by 1
  10. 2022Neural Contrastive Clustering: Fully Unsupervised Bias Reduction for Sentiment Classificationcited by 0
  11. 2025Community Detection on Model Explanation Graphs for Explainable AIcited by 0
  12. 2026Fair Feature Importance Scores via Feature Occlusion and Permutationcited by 0
1 more
  1. 2026Null importance: Disentangling relevance for interpretable machine learningcited by 0