Men Also Do Laundry: Multi-Attribute Bias Amplification

Dora Zhao

Jerone T. A. Andrews

Alice Xiang

NeurIPS 2022



As computer vision systems become more widely deployed, there is increasing concern from both the research community and the public that these systems are not only reproducing but amplifying harmful social biases. The phenomenon of bias amplification, which is the focus of this work, refers to models amplifying inherent training set biases at test time. Existing metrics measure bias amplification with respect to single annotated attributes (e.g., computer). However, several visual datasets consist of images with multiple attribute annotations. We show models can learn to exploit correlations with respect to multiple attributes (e.g., {computer, keyboard}), which are not accounted for by current metrics. In addition, \new{we show} current metrics can give the erroneous impression that minimal or no bias amplification has occurred as they involve aggregating over positive and negative values. Further, these metrics lack a clear desired value, making them difficult to interpret. To address these shortcomings, we propose a new metric: Multi-Attribute Bias Amplification. We validate our proposed metric through an analysis of gender bias amplification on the COCO and imSitu datasets. Finally, we benchmark bias mitigation methods using our proposed metric, suggesting possible avenues for future bias mitigation efforts.

Related Publications

A View From Somewhere: Human-Centric Face Representations

ICLR, 2023
Jerone T. A. Andrews, Przemyslaw Joniak, Alice Xiang

Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks. Besides, categorical labels can fail to reflect the continuous nature of human phenotypic diversity, making i…

Considerations for Ethical Speech Recognition Datasets

WSDM, 2023
Orestis Papakyriakopoulos, Alice Xiang

Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects’ protection or user needs into considerat…

Causality for Temporal Unfairness Evaluation and Mitigation

NeurIPS, 2022
Aida Rahmattalabi, Alice Xiang

Recent interests in causality for fair decision-making systems has been accompanied with great skepticism due to practical and epistemological challenges with applying existing causal fairness approaches. Existing works mainly seek to remove the causal effect of social categ…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.