Data to 7 Oct 2026

Mitigating Unwanted Biases with Adversarial Learning

arXiv 1801.07593 ↗First posted 22 Jan 2018cs.LG cs.AI cs.CYcited by 663

Not on the map. Why?

Abstract (arXiv)

Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a framework for mitigating such biases by including a variable for the group of interest and simultaneously learning a predictor and an adversary. The input to the network X, here text or census data, produces a prediction Y, such as an analogy completion or income bracket, while the adversary tries to model a protected variable Z, here gender or zip code. The objective is to maximize the predictor's ability to predict Y while minimizing the adversary's ability to predict Z. Applied to analogy completion, this method results in accurate predictions that exhibit less evidence of stereotyping Z. When applied to a classification task using the UCI Adult (Census) Dataset, it results in a predictive model that does not lose much accuracy while achieving very close to equality of odds (Hardt, et al., 2016). The method is flexible and applicable to multiple definitions of fairness as well as a wide range of gradient-based learning models, including both regression and classification tasks.

Key facts. Cited by 663 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 122; 2022: 154; 2023: 142; 2024: 107; 2025: 84; 2026: 54.

663 papers.

Sort:

By area:

2023Bias and Fairness in Large Language Models: A Surveycited by 626
2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
2023LEACE: Perfect linear concept erasure in closed formcited by 254
2021A survey on datasets for fairness-aware machine learningcited by 157
2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 155
2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 149
2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
2021FairFed: Enabling Group Fairness in Federated Learningcited by 114
2021Fair Mixup: Fairness via Interpolationcited by 109

38 more

2021Re-imagining Algorithmic Fairness in India and Beyondcited by 102
2022Linear Adversarial Concept Erasurecited by 98
2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 95
2021Trustworthy AI: A Computational Perspectivecited by 93
2021Bias in Machine Learning Software: Why? How? What to do?cited by 92
2021A Survey on Gender Bias in Natural Language Processingcited by 89
2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
2021Fairness in Credit Scoring: Assessment, Implementation and Profit Implicationscited by 65
2021Fairness via Representation Neutralizationcited by 63
2022Theories of "Gender" in NLP Bias Researchcited by 62
2022You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environmentscited by 62
2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
2021Fair Feature Distillation for Visual Recognitioncited by 59
2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
2021Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentationcited by 57
2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
2022Improving the Fairness of Chest X-ray Classifierscited by 52
2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
2021Understanding and Mitigating Annotation Bias in Facial Expression Recognitioncited by 50
2021Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipelinecited by 49
2021Sample Selection for Fair and Robust Trainingcited by 48
2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
2024FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Modelscited by 47
2024A Decade's Battle on Dataset Bias: Are We There Yet?cited by 46
2021Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Featurescited by 45
2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Biascited by 43
2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40

50 most cited of 663 All 663 (JSON)