mlsanityData to 7 Oct 2026

Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction

arXiv 1807.00199 ↗First posted 30 Jun 2018cs.LG stat.MLcited by 77

Not on the map. Why?

Abstract (arXiv)

Recidivism prediction scores are used across the USA to determine sentencing and supervision for hundreds of thousands of inmates. One such generator of recidivism prediction scores is Northpointe's Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) score, used in states like California and Florida, which past research has shown to be biased against black inmates according to certain measures of fairness. To counteract this racial bias, we present an adversarially-trained neural network that predicts recidivism and is trained to remove racial bias. When comparing the results of our model to COMPAS, we gain predictive accuracy and get closer to achieving two out of three measures of fairness: parity and equality of odds. Our model can be generalized to any prediction and demographic. This piece of research contributes an example of scientific replication and simplification in a high-stakes real-world application like recidivism prediction.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 29; 2023: 14; 2024: 8; 2025: 4; 2026: 3.

77 papers.

Sort:

By area:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  3. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  4. 2021Fairness via Representation Neutralizationcited by 63
  5. 2022Improving the Fairness of Chest X-ray Classifierscited by 52
  6. 2022Detecting Shortcut Learning for Fair Medical AI using Shortcut Testingcited by 52
  7. 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
  8. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  9. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  10. 2024Identifying Implicit Social Biases in Vision-Language Modelscited by 27
  11. 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
  12. 2022FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learningcited by 22
38 more
  1. 2021Fairness without the sensitive attribute via Causal Variational Autoencodercited by 21
  2. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  3. 2021Removing biased data to improve fairness and accuracycited by 17
  4. 2021Modeling Techniques for Machine Learning Fairness: A Surveycited by 17
  5. 2023On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representationscited by 17
  6. 2022Fair Bayes-Optimal Classifiers Under Predictive Paritycited by 16
  7. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  8. 2021Fair Enough: Searching for Sufficient Measures of Fairnesscited by 14
  9. 2022Fairness Score and Process Standardization: Framework for Fairness Certification in Artificial Intelligence Systemscited by 14
  10. 2021Towards Equity and Algorithmic Fairness in Student Grade Predictioncited by 13
  11. 2023Learning for Counterfactual Fairness from Observational Datacited by 13
  12. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  13. 2022Input-agnostic Certified Group Fairness via Gaussian Parameter Smoothingcited by 11
  14. 2022How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shiftscited by 11
  15. 2021Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice modelscited by 10
  16. 2021AI Fairness via Domain Adaptationcited by 8
  17. 2021Fairness in Missing Data Imputationcited by 8
  18. 2022Towards Equal Opportunity Fairness through Adversarial Learningcited by 8
  19. 2022A Fair Pricing Model via Adversarial Learningcited by 7
  20. 2021End-To-End Bias Mitigation: Removing Gender Bias in Deep Learningcited by 6
  21. 2021Can Information Flows Suggest Targets for Interventions in Neural Circuits?cited by 6
  22. 2023Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groupscited by 6
  23. 2023Fairness and Sequential Decision Making: Limits, Lessons, and Opportunitiescited by 5
  24. 2023Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspectscited by 5
  25. 2022fairlib: A Unified Framework for Assessing and Improving Classification Fairnesscited by 4
  26. 2022Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Talecited by 4
  27. 2022Fairness-aware Regression Robust to Adversarial Attackscited by 4
  28. 2023Consistent End-to-End Estimation for Counterfactual Fairnesscited by 4
  29. 2021Fairness-aware Summarization for Justified Decision-Makingcited by 3
  30. 2023Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Biascited by 3
  31. 2024Debiased Noise Editing on Foundation Models for Fair Medical Image Classificationcited by 3
  32. 2024FairREAD: Re-fusing Demographic Attributes after Disentanglement for Fair Medical Image Classificationcited by 3
  33. 2021Using Adversarial Debiasing to Remove Bias from Word Embeddingscited by 2
  34. 2022Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifierscited by 2
  35. 2022Gradient Based Activations for Accurate Bias-Free Learningcited by 2
  36. 2023Improving Identity-Robustness for Face Modelscited by 2
  37. 2023TrojFair: Trojan Fairness Attackscited by 2
  38. 2024Learning Fairer Representations with FairVICcited by 2

50 most cited of 77 All 77 (JSON)