paper-with-me

홈 › Papers

Multiaccurate Proxies for Downstream Fairness

2021-07-09 · Emily Diana, Wesley Gill, Michael Kearns, Krishnaram Kenthapadi, Aaron Roth, Saeed Sharifi-Malvajerdi

We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time -- in other words, how can we train a model to be fair by race when we don't have data about race? We adopt a fairness pipeline perspective, in which an "upstream" learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general "downstream" learner -- with minimal assumptions on their prediction task -- to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies, and conduct an experimental evaluation. In general, multiaccuracy is much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.

📄 PDF Abstract BibTeX arXiv:2107.04423

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessGeneralization Bounds

Similar Papers 제목 키워드 기반

Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive Attributes

2022-10-06 · Zhaowei Zhu, Yuanshun Yao, Jiankai Sun, Hang Li 외

Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry frequently adopts is using off-the-shelf…

Fairness

Stability and Multigroup Fairness in Ranking with Uncertain Predictions

2024-02-14 · Siddartha Devic, Aleksandra Korolova, David Kempe, Vatsal Sharan

Rankings are ubiquitous across many applications, from search engines to hiring committees. In practice, many rankings are derived from the output of predictors. However, when predictors trained for classification tasks …

Fairness

Model Debiasing via Gradient-based Explanation on Representation

2023-05-20 · Jindi Zhang, Luning Wang, Dan Su, Yongxiang Huang 외

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled …

DisentanglementFairnessmodelRepresentation Learning

Unaware Fairness: Hierarchical Random Forest for Protected Classes

2021-06-30 · Xian Li

Procedural fairness has been a public concern, which leads to controversy when making decisions with respect to protected classes, such as race, social status, and disability. Some protected classes can be inferred accor…

Fairness

Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond

2025-07-09 · Marina Ceccon, Giandomenico Cornacchia, Davide Dalle Pezze, Alessandro Fabris 외 arxiv

Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discriminat…