English
Related papers

Related papers: Practical Bias Mitigation through Proxy Sensitive …

200 papers

Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model…

Machine Learning · Statistics 2025-07-15 Ricardo Inácio , Zafeiris Kokkinogenis , Vitor Cerqueira , Carlos Soares

Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these models are data-driven, they inherit biases from the…

Machine Learning · Computer Science 2025-03-18 Lin-Chun Huang , Ching Chieh Tsao , Fang-Yi Su , Jung-Hsien Chiang

Training a semantic segmentation model requires a large amount of pixel-level annotation, hampering its application at scale. With computer graphics, we can generate almost unlimited training data with precise annotation. However,a deep…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Tong Shen , Dong Gong , Wei Zhang , Chunhua Shen , Tao Mei

Machine learning systems are increasingly being used to make impactful decisions such as loan applications and criminal justice risk assessments, and as such, ensuring fairness of these systems is critical. This is often challenging as the…

Machine Learning · Computer Science 2020-12-18 YooJung Choi , Meihua Dang , Guy Van den Broeck

Modern machine learning (ML) models are becoming increasingly popular and are widely used in decision-making systems. However, studies have shown critical issues of ML discrimination and unfairness, which hinder their adoption on high-stake…

Machine Learning · Computer Science 2023-06-01 Yueqing Liang , Canyu Chen , Tian Tian , Kai Shu

Organizations cannot address demographic disparities that they cannot see. Recent research on machine learning and fairness has emphasized that awareness of sensitive attributes, such as race and sex, is critical to the development of…

Computers and Society · Computer Science 2019-12-16 Miranda Bogen , Aaron Rieke , Shazeda Ahmed

Machine learning systems are notoriously prone to biased predictions about certain demographic groups, leading to algorithmic fairness issues. Due to privacy concerns and data quality problems, some demographic information may not be…

Machine Learning · Computer Science 2024-12-31 Yingtao Luo , Zhixun Li , Qiang Liu , Jun Zhu

To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…

Machine Learning · Computer Science 2023-02-21 Sébastien Gambs , Rosin Claude Ngueveu

We study the problem of collecting a cohort or set that is balanced with respect to sensitive groups when group membership is unavailable or prohibited from use at deployment time. Specifically, our deployment-time collection mechanism does…

Machine Learning · Computer Science 2024-06-19 Siqi Deng , Emily Diana , Michael Kearns , Aaron Roth

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Aditya Parikh , Stella Frank , Sneha Das , Aasa Feragen

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…

Machine Learning · Computer Science 2022-01-27 Emily Diana , Wesley Gill , Michael Kearns , Krishnaram Kenthapadi , Aaron Roth , Saeed Sharifi-Malvajerdi

Most existing fair classifiers rely on sensitive attributes to achieve fairness. However, for many scenarios, we cannot obtain sensitive attributes due to privacy and legal issues. The lack of sensitive attributes challenges many existing…

Machine Learning · Computer Science 2024-10-04 Huaisheng Zhu , Enyan Dai , Hui Liu , Suhang Wang

Data containing human or social attributes may over- or under-represent groups with respect to salient social attributes such as gender or race, which can lead to biases in downstream applications. This paper presents an algorithmic…

Machine Learning · Computer Science 2020-07-01 L. Elisa Celis , Vijay Keswani , Nisheeth K. Vishnoi

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…

Machine Learning · Computer Science 2025-07-25 Bruno Scarone , Alfredo Viola , Renée J. Miller , Ricardo Baeza-Yates

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Miao Zhang , Zee fryer , Ben Colman , Ali Shahriyari , Gaurav Bharaj

The widespread adoption of generative AI models has raised growing concerns about representational harm and potential discriminatory outcomes. Yet, despite growing literature on this topic, the mechanisms by which bias emerges - especially…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Xiaofeng Zhang , Michelle Lin , Simon Lacoste-Julien , Aaron Courville , Yash Goyal

The issue of fairness in machine learning models has recently attracted a lot of attention as ensuring it will ensure continued confidence of the general public in the deployment of machine learning systems. We focus on mitigating the harm…

Machine Learning · Statistics 2021-02-24 Thomas Kehrenberg , Zexun Chen , Novi Quadrianto

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 proxy models to…

Machine Learning · Computer Science 2023-02-01 Zhaowei Zhu , Yuanshun Yao , Jiankai Sun , Hang Li , Yang Liu

Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute information and label information of the data points. In many…

Machine Learning · Computer Science 2021-02-18 Pranjal Awasthi , Alex Beutel , Matthaeus Kleindessner , Jamie Morgenstern , Xuezhi Wang

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Kaixin Zhang , Zhixiang Yuan , Tao Huang