Deleting the wiki page 'Researchers Reduce Bias in aI Models while Maintaining Or Improving Accuracy' cannot be undone. Continue?
1
Researchers Reduce Bias in aI Models while Maintaining Or Improving Accuracy
Abby McPhee edited this page 2 weeks ago
Machine-learning models can fail when they try to make forecasts for people who were underrepresented in the datasets they were trained on.
For swwwwiki.coresv.net example, a design that forecasts the very best treatment option for someone with a persistent disease may be trained using a dataset that contains mainly male clients. That design may make inaccurate predictions for female clients when deployed in a hospital.
To improve outcomes, can attempt stabilizing the training dataset by removing data points till all subgroups are represented equally. While dataset balancing is appealing, it frequently requires removing large quantity of information, harming the design's general efficiency.
MIT scientists developed a brand-new method that determines and yewiki.org gets rid of specific points in a training dataset that contribute most to a design's failures on minority subgroups. By getting rid of far fewer datapoints than other methods, this strategy maintains the general precision of the design while improving its performance concerning underrepresented groups.
In addition, the strategy can recognize concealed sources of predisposition in a training dataset that lacks labels. Unlabeled data are much more prevalent than identified information for lots of applications.
This approach might likewise be integrated with other methods to enhance the fairness of machine-learning designs released in high-stakes circumstances. For instance, it might at some point help guarantee underrepresented clients aren't misdiagnosed due to a biased AI design.
"Many other algorithms that attempt to address this problem assume each datapoint matters as much as every other datapoint. In this paper, we are showing that assumption is not true. There specify points in our dataset that are adding to this bias, and we can find those data points, eliminate them, and get better efficiency," says Kimia Hamidieh, an electrical engineering and computer system science (EECS) graduate trainee at MIT and co-lead author of a paper on this method.
She wrote the paper with co-lead authors Saachi Jain PhD '24 and fellow EECS graduate trainee Kristian Georgiev
Delete Page