Measuring Fairness in Generative Models
This work addresses fairness assessment in generative models, which is crucial for applications like law enforcement, but it appears incremental as it builds on prior metrics and frameworks.
The paper tackles the problem of evaluating fairness in deep generative models by reviewing existing fairness metrics and highlighting their weaknesses, then proposes a performance benchmark framework for assessing alternative metrics.
Deep generative models have made much progress in improving training stability and quality of generated data. Recently there has been increased interest in the fairness of deep-generated data. Fairness is important in many applications, e.g. law enforcement, as biases will affect efficacy. Central to fair data generation are the fairness metrics for the assessment and evaluation of different generative models. In this paper, we first review fairness metrics proposed in previous works and highlight potential weaknesses. We then discuss a performance benchmark framework along with the assessment of alternative metrics.