A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild
This work casts doubt on the practice of predicting subjective traits like employability from appearances, highlighting limitations in embedding appearance bias in machine learning, which is incremental as it builds on prior social psychology research.
The study investigated whether state-of-the-art face processing technology can learn human-like appearance biases, finding that features from FaceNet predicted bias scores for manipulated faces but not for randomly generated faces, and failed to correlate with politicians' vote shares based on perceived competence.
Research in social psychology has shown that people's biased, subjective judgments about another's personality based solely on their appearance are not predictive of their actual personality traits. But researchers and companies often utilize computer vision models to predict similarly subjective personality attributes such as "employability." We seek to determine whether state-of-the-art, black box face processing technology can learn human-like appearance biases. With features extracted with FaceNet, a widely used face recognition framework, we train a transfer learning model on human subjects' first impressions of personality traits in other faces as measured by social psychologists. We find that features extracted with FaceNet can be used to predict human appearance bias scores for deliberately manipulated faces but not for randomly generated faces scored by humans. Additionally, in contrast to work with human biases in social psychology, the model does not find a significant signal correlating politicians' vote shares with perceived competence bias. With Local Interpretable Model-Agnostic Explanations (LIME), we provide several explanations for this discrepancy. Our results suggest that some signals of appearance bias documented in social psychology are not embedded by the machine learning techniques we investigate. We shed light on the ways in which appearance bias could be embedded in face processing technology and cast further doubt on the practice of predicting subjective traits based on appearances.