Towards intersectionality in machine learning: Including more identities, handling underrepresentation, and performing evaluation
Research in machine learning fairness has historically considered a single binary
demographic attribute; however, the reality is of course far more complicated. In this work …
demographic attribute; however, the reality is of course far more complicated. In this work …
Fair attribute classification through latent space de-biasing
VV Ramaswamy, SSY Kim… - Proceedings of the …, 2021 - openaccess.thecvf.com
Fairness in visual recognition is becoming a prominent and critical topic of discussion as
recognition systems are deployed at scale in the real world. Models trained from data in …
recognition systems are deployed at scale in the real world. Models trained from data in …
Fairness in biometrics: a figure of merit to assess biometric verification systems
T de Freitas Pereira, S Marcel - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Machine learning-based (ML) systems are being largely deployed since the last decade in a
myriad of scenarios impacting several instances in our daily lives. With this vast sort of …
myriad of scenarios impacting several instances in our daily lives. With this vast sort of …
Retiring DP: New Distribution-Level Metrics for Demographic Parity
Demographic parity is the most widely recognized measure of group fairness in machine
learning, which ensures equal treatment of different demographic groups. Numerous works …
learning, which ensures equal treatment of different demographic groups. Numerous works …
Towards fairness in personalized ads using impression variance aware reinforcement learning
Variances in ad impression outcomes across demographic groups are increasingly
considered to be potentially indicative of algorithmic bias in personalized ads systems …
considered to be potentially indicative of algorithmic bias in personalized ads systems …
Cat: Controllable attribute translation for fair facial attribute classification
J Li, W Abd-Almageed - European Conference on Computer Vision, 2022 - Springer
As the social impact of visual recognition has been under scrutiny, several protected-
attribute balanced datasets emerged to address dataset bias in imbalanced datasets …
attribute balanced datasets emerged to address dataset bias in imbalanced datasets …
On the Maximal Local Disparity of Fairness-Aware Classifiers
Fairness has become a crucial aspect in the development of trustworthy machine learning
algorithms. Current fairness metrics to measure the violation of demographic parity have the …
algorithms. Current fairness metrics to measure the violation of demographic parity have the …
A Canonical Data Transformation for Achieving Inter-and Within-group Fairness
Increases in the deployment of machine learning algorithms for applications that deal with
sensitive data have brought attention to the issue of fairness in machine learning. Many …
sensitive data have brought attention to the issue of fairness in machine learning. Many …
Evaluating gender-neutral training data for automated image captioning
Amassing large-scale datasets used to train machine learning algorithms often includes
crowd-sourcing or web scraping. The data resulting from these approaches can carry …
crowd-sourcing or web scraping. The data resulting from these approaches can carry …
Balancing Fairness and Accuracy in Data-Restricted Binary Classification
Applications that deal with sensitive information may have restrictions placed on the data
available to a machine learning (ML) classifier. For example, in some applications, a …
available to a machine learning (ML) classifier. For example, in some applications, a …