According to a new study, explanation methods that help users determine whether to trust machine-learning model predictions can be less accurate for disadvantaged subgroups. Machine-learning algorithms are sometimes employed to assist human decision-makers when the stakes are high. For example, a
MIT researchers find that the explanation methods designed to help users determine whether to trust a machine-learning model’s predictions can perpetuate biases and lead to worse outcomes for people from disadvantaged groups. Credit: Jose-Luis Olivares, MIT with images from iStockphoto
However, are these explanation methods fair? If an explanation method provides better approximations for men than for women, or for white people than for black people,users may be more inclined to trust the model’s predictions for some people but not for others.scientists carefully examined the fairness of some widely used explanation methods.
Balagopalan wrote the paper with CSAIL graduate students Haoran Zhang and Kimia Hamidieh; CSAIL postdoc Thomas Hartvigsen; Frank Rudzicz, associate professor of computer science at the University of Toronto; and senior author Marzyeh Ghassemi, an assistant professor and head of the Healthy ML Group. The research will be presented at the ACM Conference on Fairness, Accountability, and Transparency.
With these metrics, they searched for fidelity gaps using two types of explanation models that were trained on four real-world datasets for high-stakes situations, such as predicting whether a patient dies in the ICU, whether a defendant reoffends, or whether a law school applicant will pass the bar exam. Each dataset contained protected attributes, like the sex and race of individual people.
Australia Latest News, Australia Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
AI Seems to Be Better at Distributing Wealth Than Humans Are, Study HintsArtificial intelligence (AI) can devise methods of wealth distribution that are more popular than systems designed by people, new research suggests.
Read more »
Val Kilmer's Dialogue in 'Top Gun: Maverick' Was Read by AI Because He Can't Speak AnymoreOne of the most moving scenes in 'Top Gun: Maverick' involves an AI voice speaking in place of leading man Val Kilmer, who can no longer speak.
Read more »
DeepMind’s AI develops popular policy for distributing public moneyDeepMind researchers have trained an AI system to find a popular policy for distributing public funds in an online game – but they also warn against “AI government”
Read more »
'Fair' AI could help redress bias against Black US homebuyersPioneering reparations programmes meant to address decades of US housing discrimination against Black homebuyers could get a boost from AI decision making
Read more »
FIFA will track players’ bodies using AI to make offside calls at 2022 World CupAnother step towards automated referees
Read more »
Researchers use AI to predict crime, biased policing in major U.S. cities like L.A.A group of social scientists out of Chicago has developed a machine learning model it says not only predicts crime a week in advance, but has also uncovered biased policing in eight major U.S. cities, including Los Angeles.
Read more »