paper-with-me

홈 › Papers

Towards Equal Opportunity Fairness through Adversarial Learning

2022-03-12 · Xudong Han, Timothy Baldwin, Trevor Cohn

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.

📄 PDF Abstract BibTeX arXiv:2203.06317

Code (1)

HanXudong/fairlib 공식 구현 pytorch

Tasks

Fairness

Similar Papers 제목 키워드 기반

Towards Equal Opportunity Fairness through Adversarial Learning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

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…

Fairness

Optimising Equal Opportunity Fairness in Model Training

2022-05-05 · NAACL 2022 7 · Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin 외

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…

Fairnessmodel

A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity

2018-09-10 · Hoda Heidari, Michele Loi, Krishna P. Gummadi, Andreas Krause

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…

FairnessPhilosophy

Algorithmic Tradeoffs in Fair Lending: Profitability, Compliance, and Long-Term Impact

2025-05-08 · Aayam Bansal

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…

Fairness

Learning Adversarially Fair and Transferable Representations

2018-02-17 · ICML 2018 7 · David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel

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