References

• 2018Mitigating Unwanted Biases with Adversarial Learning1,387 cited
• 2011Data preprocessing techniques for classification without discrimination1,304 cited
• 2018FairGAN: Fairness-aware Generative Adversarial Networks379 cited
• 2023Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale340 cited
• 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations282 cited
• 2019REPAIR: Removing Representation Bias by Dataset Resampling228 cited
• 2019Multiaccuracy189 cited
• 2019Bias Mitigation Post-processing for Individual and Group Fairness135 cited
• 2021Fair Attribute Classification through Latent Space De-biasing123 cited
• 2023Social Biases through the Text-to-Image Generation Lens117 cited
• 2019Discovering Fair Representations in the Data Domain108 cited
• 2020Fairness by Learning Orthogonal Disentangled Representations69 cited
• 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?55 cited
• 2023The Capacity for Moral Self-Correction in Large Language Models53 cited
• 2020Towards Accuracy-Fairness Paradox32 cited