Towards Equal Opportunity Fairness through Adversarial Learning
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.
Code (1)
Tasks
FairnessSimilar Papers 제목 키워드 기반
Towards Equal Opportunity Fairness through Adversarial Learning
Adversarial training is a common approach for bias mitigation in natural language processing. Although most work on debiasing is based around the equal opportunity criterion, it is not explicitly captured in standard adv…
FairnessOptimising Equal Opportunity Fairness in Model Training
Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debias…
FairnessmodelA Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity
We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conce…
FairnessPhilosophyAlgorithmic Tradeoffs in Fair Lending: Profitability, Compliance, and Long-Term Impact
As financial institutions increasingly rely on machine learning models to automate lending decisions, concerns about algorithmic fairness have risen. This paper explores the tradeoff between enforcing fairness constraint…
FairnessLearning Adversarially Fair and Transferable Representations
In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectiv…
FairnessRepresentation LearningTransfer Learning