Machine-learning designs can fail when they attempt to make forecasts for individuals who were underrepresented in the datasets they were trained on.
For example, a design that forecasts the finest treatment option for somebody with a persistent illness may be trained using a dataset that contains mainly male clients. That model might make incorrect forecasts for female clients when deployed in a health center.
To improve outcomes, engineers can try stabilizing the training dataset by getting rid of data points up until all subgroups are represented similarly. While dataset balancing is promising, it often needs eliminating large quantity of data, injuring the model's general performance.
MIT researchers established a brand-new method that identifies and gets rid of specific points in a training dataset that contribute most to a model's failures on minority subgroups. By getting rid of far fewer datapoints than other approaches, this technique maintains the overall accuracy of the model while improving its efficiency concerning underrepresented groups.
In addition, the method can identify covert sources of bias in a training dataset that does not have labels. Unlabeled information are much more prevalent than labeled information for lots of applications.
This technique could likewise be combined with other methods to improve the fairness of machine-learning models released in high-stakes situations. For example, it may someday assist guarantee underrepresented clients aren't misdiagnosed due to a biased AI model.
"Many other algorithms that try to resolve this issue assume each datapoint matters as much as every other datapoint. In this paper, we are revealing that presumption is not true. There are specific points in our dataset that are contributing to this predisposition, and we can discover those data points, eliminate them, and improve performance," says Kimia Hamidieh, an electrical engineering and computer technology (EECS) graduate trainee at MIT and co-lead author of a paper on this method.
She composed the paper with co-lead authors Saachi Jain PhD '24 and fellow EECS graduate trainee Kristian Georgiev
1
Researchers Reduce Bias in aI Models while Maintaining Or Improving Accuracy
lesterscruggs edited this page 2 months ago