Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

Harsha Nori · Rich Caruana · Zhiqi Bu · Judy Hanwen Shen · Janardhan Kulkarni

Keywords: [ Social Aspects of Machine Learning ] [ Privacy, Anonymity, and Security ]


We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.

Chat is not available.