paper-with-me

홈 › Papers

Fairness-Aware PAC Learning from Corrupted Data

2021-02-11 · Nikola Konstantinov, Christoph H. Lampert

Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known about the robustness of these methods to data corruption. In this work we consider fairness-aware learning under worst-case data manipulations. We show that an adversary can in some situations force any learner to return an overly biased classifier, regardless of the sample size and with or without degrading accuracy, and that the strength of the excess bias increases for learning problems with underrepresented protected groups in the data. We also prove that our hardness results are tight up to constant factors. To this end, we study two natural learning algorithms that optimize for both accuracy and fairness and show that these algorithms enjoy guarantees that are order-optimal in terms of the corruption ratio and the protected groups frequencies in the large data limit.

📄 PDF Abstract BibTeX arXiv:2102.06004

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessPAC learning

Similar Papers 제목 키워드 기반

FairSAM: Fair Classification on Corrupted Data Through Sharpness-Aware Minimization

2025-03-29 · Yucong Dai, Jie Ji, Xiaolong Ma, Yongkai Wu

Image classification models trained on clean data often suffer from significant performance degradation when exposed to testing corrupted data, such as images with impulse noise, Gaussian noise, or environmental noise. T…

Fairnessimage-classificationImage Classification

Adversarial Attacks on Fairness of Graph Neural Networks

2023-10-20 · Binchi Zhang, Yushun Dong, Chen Chen, Yada Zhu 외

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly …

Fairness

FORML: Learning to Reweight Data for Fairness

2022-02-03 · Bobby Yan, Skyler Seto, Nicholas Apostoloff

Machine learning models are trained to minimize the mean loss for a single metric, and thus typically do not consider fairness and robustness. Neglecting such metrics in training can make these models prone to fairness v…

Fairnessimage-classificationImage ClassificationMeta-Learning+1

Fairness in multi-class multi-group classification problems via contextial coherent risk measures

2026-08-31 · Darinka Dentcheva, Xiangyu Tian arxiv

We propose a new design of fair classifiers for multi-class classification problems in the presence of vector-valued sensitive attributes. In that scenario each sensitive attribute has multiple values and forms several g…

Multi-class Classification

Towards Fairness-Aware Multi-Objective Optimization

2022-07-22 · Guo Yu, Lianbo Ma, Wei Du, Wenli Du 외

Recent years have seen the rapid development of fairness-aware machine learning in mitigating unfairness or discrimination in decision-making in a wide range of applications. However, much less attention has been paid to…

BIG-bench Machine LearningDecision MakingFairnessMultiobjective Optimization