paper-with-me

홈 › Papers

Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness

2022-02-22 · Carolyn Ashurst, Ryan Carey, Silvia Chiappa, Tom Everitt

In addition to reproducing discriminatory relationships in the training data, machine learning systems can also introduce or amplify discriminatory effects. We refer to this as introduced unfairness, and investigate the conditions under which it may arise. To this end, we propose introduced total variation as a measure of introduced unfairness, and establish graphical conditions under which it may be incentivised to occur. These criteria imply that adding the sensitive attribute as a feature removes the incentive for introduced variation under well-behaved loss functions. Additionally, taking a causal perspective, introduced path-specific effects shed light on the issue of when specific paths should be considered fair.

📄 PDF Abstract BibTeX arXiv:2202.10816

Code (0)

등록된 구현이 없습니다.

Tasks

Attribute

Similar Papers 제목 키워드 기반

A Causal Bayesian Networks Viewpoint on Fairness

2019-07-15 · Silvia Chiappa, William S. Isaac

We offer a graphical interpretation of unfairness in a dataset as the presence of an unfair causal path in the causal Bayesian network representing the data-generation mechanism. We use this viewpoint to revisit the rece…

Fairness

Towards Auditability for Fairness in Deep Learning

2020-11-30 · Ivoline C. Ngong, Krystal Maughan, Joseph P. Near

Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions. We present…

Deep LearningFairnessPredictionSensitivity

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms

2022-04-21 · Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton, Hao-Fei Cheng 외

Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Most existing algorithms, however, are agn…

Fairness

Assessing Predictive Models for Fairness Based on Movement Patterns

2026-05-22 · Francesco Lettich, Mario A. Nascimento, Chiara Pugliese, Chiara Renso arxiv

Assessing the spatial fairness of predictive models involves establishing whether they are statistically penalizing (favoring) individuals associated with certain geographical locations. Literature on this topic makes th…

Fair inference on error-prone outcomes

2020-03-17 · Laura Boeschoten, Erik-Jan van Kesteren, Ayoub Bagheri, Daniel L. Oberski

Fair inference in supervised learning is an important and active area of research, yielding a range of useful methods to assess and account for fairness criteria when predicting ground truth targets. As shown in recent w…

counterfactualFairness