mlsanityData to 14 Oct 2026

Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation

arXiv 2209.09592 ↗First posted 20 Sep 2022cs.LG cs.IRcited by 7

Not on the map. Why?

Abstract (arXiv)

The goal of this work is to help mitigate the already existing gender wage gap by supplying unbiased job recommendations based on resumes from job seekers. We employ a generative adversarial network to remove gender bias from word2vec representations of 12M job vacancy texts and 900k resumes. Our results show that representations created from recruitment texts contain algorithmic bias and that this bias results in real-world consequences for recommendation systems. Without controlling for bias, women are recommended jobs with significantly lower salary in our data. With adversarially fair representations, this wage gap disappears, meaning that our debiased job recommendations reduce wage discrimination. We conclude that adversarial debiasing of word representations can increase real-world fairness of systems and thus may be part of the solution for creating fairness-aware recommendation systems.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 16 of its 38 references that are in the map. First posted on arXiv 20 Sep 2022.

Builds on

16 of 38 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  6. 2016Semantics derived automatically from language corpora contain human-like biasescited by 901
  7. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  8. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  9. 2019Measuring Bias in Contextualized Word Representationscited by 276
  10. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  11. 2015Censoring Representations with an Adversarycited by 192
  12. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
4 more
  1. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 103
  2. 2020FairRec: Fairness-aware News Recommendation with Decomposed Adversarial Learningcited by 44
  3. 2021Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classificationcited by 20
  4. 2018Responsible team players wanted: an analysis of soft skill requirements in job advertisementscited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2023A Survey on Fairness-aware Recommender Systemscited by 14
  2. 2024Measuring Bias in a Ranked List using Term-based Representationscited by 4
  3. 2025Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairnesscited by 3
  4. 2023Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluationcited by 2
  5. 2026Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practicescited by 1
  6. 2024Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainabilitycited by 0
  7. 2025FnRGNN: Distribution-aware Fairness in Graph Neural Networkcited by 0