Matched sample selection with GANs for mitigating attribute confounding

Abstract

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark datasets make it difficult to separate algorithmic bias from dataset bias. To mitigate such attribute confounding during bias analysis, we propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes. Our matching approach first projects real images onto a generative adversarial network (GAN)'s latent space in a manner that preserves semantic attributes. It then finds image matches in this latent space across a chosen protected attribute, yielding a dataset where semantic and perceptual attributes are balanced across the protected attribute. We validate projection and matching strategies with qualitative, quantitative, and human annotation experiments. We demonstrate our work in the context of gender bias in multiple open-source facial-recognition classifiers and find that bias persists after removing key confounders via matching. Code and documentation to reproduce the results here and apply the methods to new data is available at https://github.com/csinva/matching-with-gans .

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Matching Methods for Causal Inference: A Review and a Look Forward
• Learning Face Representation from Scratch
• Invertible Conditional GANs for image editing
• Precise Recovery of Latent Vectors from Generative Adversarial Networks
• CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
• Age and gender bias in pedestrian detection algorithms
• Balance Regularized Neural Network Models for Causal Effect Estimation