论文标题
迈向准确性悖论：基于对抗性示例的数据增强，用于视觉偏见
Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
论文作者
论文摘要
机器学习公平涉及在解决目标任务时对某些受保护或敏感人群的偏见。本文在图像分类任务的背景下研究了伪造问题。我们对面部属性识别的数据分析证明了（1）模型偏差不平衡训练数据分布的归因，以及（2）对抗性示例在平衡数据分布中的潜力。因此，我们有动力采用对抗性示例来增强训练数据进行视觉看法。具体来说，为了确保对抗性概括以及交叉任务的可转让性，我们建议将目标任务分类器培训，偏差任务分类器培训和对抗性示例生成的操作进行授课。生成的对抗性示例通过以在线方式平衡分布与偏差变量来补充目标任务培训数据集。对模拟和现实世界中的偏见实验的结果证明了拟议解决方案同时提高模型准确性和公平性的有效性。几次学习的初步实验进一步展示了基于对抗攻击的伪样本生成的潜力，作为弥补培训数据缺乏的替代解决方案。
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution. We are thus motivated to employ adversarial example to augment the training data for visual debiasing. Specifically, to ensure the adversarial generalization as well as cross-task transferability, we propose to couple the operations of target task classifier training, bias task classifier training, and adversarial example generation. The generated adversarial examples supplement the target task training dataset via balancing the distribution over bias variables in an online fashion. Results on simulated and real-world debiasing experiments demonstrate the effectiveness of the proposed solution in simultaneously improving model accuracy and fairness. Preliminary experiment on few-shot learning further shows the potential of adversarial attack-based pseudo sample generation as alternative solution to make up for the training data lackage.
