mlsanityData to 7 Oct 2026

Towards Equal Opportunity Fairness through Adversarial Learning

arXiv 2203.06317 ↗First posted 12 Mar 2022cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is motivated by equal opportunity, it is not explicitly captured in standard adversarial training. In this paper, we propose an augmented discriminator for adversarial training, which takes the target class as input to create richer features and more explicitly model equal opportunity. Experimental results over two datasets show that our method substantially improves over standard adversarial debiasing methods, in terms of the performance--fairness trade-off.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 20 of its 28 references that are in the map. First posted on arXiv 12 Mar 2022.

Builds on

20 of 28 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2014Certifying and removing disparate impactcited by 715
  5. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 671
  6. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  7. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  8. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 442
  9. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
  10. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  11. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  12. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
8 more
  1. 2017Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasmcited by 117
  2. 2019Conditional Learning of Fair Representationscited by 78
  3. 2018Achieving Fairness through Adversarial Learning: an Application to Recidivism Predictioncited by 77
  4. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  5. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  6. 2020Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizationscited by 40
  7. 2021Evaluating Debiasing Techniques for Intersectional Biasescited by 30
  8. 2018What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Trainingcited by 17

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 1; 2025: 1.

8 papers.

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  3. 2023Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLPcited by 11
  4. 2022Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustnesscited by 5
  5. 2022fairlib: A Unified Framework for Assessing and Improving Classification Fairnesscited by 4
  6. 2023A Brief History of Prompt: Leveraging Language Models. (Through Advanced Prompting)cited by 4
  7. 2022Systematic Evaluation of Predictive Fairnesscited by 3
  8. 2025Controllable Pareto Trade-off between Fairness and Accuracycited by 0