Machine-learning models can fail when they attempt to make predictions for individuals who were underrepresented in the datasets they were trained on.
For raovatonline.org instance, a model that anticipates the very best treatment choice for photorum.eclat-mauve.fr somebody with a chronic disease may be trained utilizing a dataset that contains mainly male clients. That design may make inaccurate forecasts for female patients when deployed in a healthcare facility.
To improve results, engineers can attempt balancing the training dataset by eliminating data points up until all subgroups are represented equally. While dataset balancing is appealing, it typically needs removing big quantity of data, hurting the model's overall performance.
MIT researchers established a new method that identifies and eliminates particular points in a training dataset that contribute most to a design's failures on minority subgroups. By removing far less datapoints than other techniques, this strategy maintains the total precision of the model while improving its efficiency regarding underrepresented groups.
In addition, the strategy can determine surprise sources of bias in a training dataset that lacks labels. Unlabeled information are even more prevalent than labeled information for lots of applications.
This approach might likewise be integrated with other techniques to improve the fairness of machine-learning designs released in high-stakes situations. For instance, it may someday help ensure underrepresented patients aren't misdiagnosed due to a biased AI design.
"Many other algorithms that attempt to resolve this problem assume each datapoint matters as much as every other datapoint. In this paper, we are showing that presumption is not real. There specify points in our dataset that are adding to this bias, and we can discover those information points, eliminate them, and get much better efficiency," states Kimia Hamidieh, an electrical engineering and computer science (EECS) graduate trainee at MIT and co-lead author of a paper on this technique.
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
Adalberto Forro edited this page 2025-02-09 09:40:20 -06:00