Learning Fair Robustness via Domain Mixup

2024-11-21 · Meiyu Zhong, Ravi Tandon

Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training, which makes the overall classifier robust, it does not necessarily provide equal amount of robustness for all classes. In this paper, we propose the use of mixup for the problem of learning fair robust classifiers, which can provide similar robustness across all classes. Specifically, the idea is to mix inputs from the same classes and perform adversarial training on mixed up inputs. We present a theoretical analysis of this idea for the case of linear classifiers and show that mixup combined with adversarial training can provably reduce the class-wise robustness disparity. This method not only contributes to reducing the disparity in class-wise adversarial risk, but also the class-wise natural risk. Complementing our theoretical analysis, we also provide experimental results on both synthetic data and the real world dataset (CIFAR-10), which shows improvement in class wise disparities for both natural and adversarial risks.

📄 PDF Abstract BibTeX arXiv:2411.14424

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

FairDD: Enhancing Fairness with domain-incremental learning in dermatological disease diagnosis

2024-12-21 · Yiqin Luo, Tianlong Gu

With the rapid advancement of deep learning technologies, artificial intelligence has become increasingly prevalent in the research and application of dermatological disease diagnosis. However, this data-driven approach …

Contrastive Learning Data Augmentation Diagnostic Fairness+1

Data Augmentation via Subgroup Mixup for Improving Fairness

2023-09-13 · Madeline Navarro, Camille Little, Genevera I. Allen, Santiago Segarra

In this work, we propose data augmentation via pairwise mixup across subgroups to improve group fairness. Many real-world applications of machine learning systems exhibit biases across certain groups due to under-represe…

Data Augmentation Fairness

Fair Mixup: Fairness via Interpolation

2021-03-11 · ICLR 2021 1 · Ching-Yao Chuang, Youssef Mroueh

Training classifiers under fairness constraints such as group fairness, regularizes the disparities of predictions between the groups. Nevertheless, even though the constraints are satisfied during training, they might n…

Data Augmentation Fairness

Who's the (Multi-)Fairest of Them All: Rethinking Interpolation-Based Data Augmentation Through the Lens of Multicalibration

2024-12-13 · Karina Halevy, Karly Hou, Charumathi Badrinath

Data augmentation methods, especially SoTA interpolation-based methods such as Fair Mixup, have been widely shown to increase model fairness. However, this fairness is evaluated on metrics that do not capture model uncer…

All Data Augmentation Fairness Holdout Set+1

C-Mixup: Improving Generalization in Regression

2022-10-11 · Huaxiu Yao, Yiping Wang, Linjun Zhang, James Zou 외

Improving the generalization of deep networks is an important open challenge, particularly in domains without plentiful data. The mixup algorithm improves generalization by linearly interpolating a pair of examples and t…

regression