paper-with-me

Papers

Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

2022-06-26 · Bang An, Zora Che, Mucong Ding, Furong Huang

The increasing reliance on ML models in high-stakes tasks has raised a major concern on fairness violations. Although there has been a surge of work that improves algorithmic fairness, most of them are under the assumption of an identical training and test distribution. In many real-world applications, however, such an assumption is often violated as previously trained fair models are often deployed in a different environment, and the fairness of such models has been observed to collapse. In this paper, we study how to transfer model fairness under distribution shifts, a widespread issue in practice. We conduct a fine-grained analysis of how the fair model is affected under different types of distribution shifts and find that domain shifts are more challenging than subpopulation shifts. Inspired by the success of self-training in transferring accuracy under domain shifts, we derive a sufficient condition for transferring group fairness. Guided by it, we propose a practical algorithm with a fair consistency regularization as the key component. A synthetic dataset benchmark, which covers all types of distribution shifts, is deployed for experimental verification of the theoretical findings. Experiments on synthetic and real datasets including image and tabular data demonstrate that our approach effectively transfers fairness and accuracy under various distribution shifts.

📄 PDF Abstract BibTeX arXiv:2206.12796

Code (1)

umd-huang-lab/transfer-fairness 공식 구현 pytorch

Tasks

Fairness

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts

2022-07-04 · Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang

Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods mainly focus on the fairness of in-distribution data. However, in real-world applications, …

Fairness

Equalized Robustness: Towards Sustainable Fairness Under Distributional Shifts

2021-09-29 · Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang

Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness metrics and algorithms mainly focus on the discrimination of model performance across different groups on in-distribution …

Fairness

Domain Adaptation meets Individual Fairness. And they get along

2022-05-01 · Debarghya Mukherjee, Felix Petersen, Mikhail Yurochkin, Yuekai Sun

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, w…

Domain AdaptationFairness

Context matters for fairness -- a case study on the effect of spatial distribution shifts

2022-06-23 · Siamak Ghodsi, Harith Alani, Eirini Ntoutsi

With the ever growing involvement of data-driven AI-based decision making technologies in our daily social lives, the fairness of these systems is becoming a crucial phenomenon. However, an important and often challengin…

Decision MakingFairness

Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains

2025-08-31 · Yumeng Lin, Dong Li, Xintao Wu, Minglai Shao 외 arxiv

Ensuring fairness and robustness in machine learning models remains a challenge, particularly under domain shifts. We present Face4FairShifts, a large-scale facial image benchmark designed to systematically evaluate fair…

Domain GeneralizationDomain Adaptation