Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing
This addresses fairness issues in machine learning for image classification tasks, particularly for protected groups, though it appears incremental as it builds on existing adversarial example methods.
The paper tackles visual debiasing in image classification by using adversarial examples to augment training data, balancing data distribution over bias variables. Results show effectiveness in improving both model accuracy and fairness on simulated and real-world experiments.
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.