Mitigating bias in algorithmic systems—a fish-eye view
Mitigating bias in algorithmic systems is a critical issue drawing attention across
communities within the information and computer sciences. Given the complexity of the …
communities within the information and computer sciences. Given the complexity of the …
Towards fairer datasets: Filtering and balancing the distribution of the people subtree in the imagenet hierarchy
Computer vision technology is being used by many but remains representative of only a few.
People have reported misbehavior of computer vision models, including offensive prediction …
People have reported misbehavior of computer vision models, including offensive prediction …
Fairness in information access systems
Recommendation, information retrieval, and other information access systems pose unique
challenges for investigating and applying the fairness and non-discrimination concepts that …
challenges for investigating and applying the fairness and non-discrimination concepts that …
Survey of social bias in vision-language models
In recent years, the rapid advancement of machine learning (ML) models, particularly
transformer-based pre-trained models, has revolutionized Natural Language Processing …
transformer-based pre-trained models, has revolutionized Natural Language Processing …
Skin deep: Investigating subjectivity in skin tone annotations for computer vision benchmark datasets
To investigate the well-observed racial disparities in computer vision systems that analyze
images of humans, researchers have turned to skin tone as a more objective annotation …
images of humans, researchers have turned to skin tone as a more objective annotation …
[HTML][HTML] Algorithmic fairness datasets: the story so far
Data-driven algorithms are studied and deployed in diverse domains to support critical
decisions, directly impacting people's well-being. As a result, a growing community of …
decisions, directly impacting people's well-being. As a result, a growing community of …
Mitigating test-time bias for fair image retrieval
We address the challenge of generating fair and unbiased image retrieval results given
neutral textual queries (with no explicit gender or race connotations), while maintaining the …
neutral textual queries (with no explicit gender or race connotations), while maintaining the …
Mitigating bias in set selection with noisy protected attributes
A Mehrotra, LE Celis - Proceedings of the 2021 ACM conference on …, 2021 - dl.acm.org
Subset selection algorithms are ubiquitous in AI-driven applications, including, online
recruiting portals and image search engines, so it is imperative that these tools are not …
recruiting portals and image search engines, so it is imperative that these tools are not …
Fair ranking with noisy protected attributes
A Mehrotra, N Vishnoi - Advances in Neural Information …, 2022 - proceedings.neurips.cc
The fair-ranking problem, which asks to rank a given set of items to maximize utility subject
to group fairness constraints, has received attention in the fairness, information retrieval, and …
to group fairness constraints, has received attention in the fairness, information retrieval, and …
When fair ranking meets uncertain inference
Existing fair ranking systems, especially those designed to be demographically fair, assume
that accurate demographic information about individuals is available to the ranking …
that accurate demographic information about individuals is available to the ranking …