Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Making AI Forget You: Data Deletion in Machine Learning

About

Intense recent discussions have focused on how to provide individuals with control over when their data can and cannot be used --- the EU's Right To Be Forgotten regulation is an example of this effort. In this paper we initiate a framework studying what to do when it is no longer permissible to deploy models derivative from specific user data. In particular, we formulate the problem of efficiently deleting individual data points from trained machine learning models. For many standard ML models, the only way to completely remove an individual's data is to retrain the whole model from scratch on the remaining data, which is often not computationally practical. We investigate algorithmic principles that enable efficient data deletion in ML. For the specific setting of k-means clustering, we propose two provably efficient deletion algorithms which achieve an average of over 100X improvement in deletion efficiency across 6 datasets, while producing clusters of comparable statistical quality to a canonical k-means++ baseline.

Antonio Ginart, Melody Y. Guan, Gregory Valiant, James Zou• 2019

Related benchmarks

TaskDatasetResultRank
Machine UnlearningCIFAR-10--
45
Machine UnlearningCIFAR-10 1.0 (test)
Test Acc95.23
24
Class UnlearningCIFAR-10 (test)--
21
Class UnlearningTiny ImageNet (test)
Df (Degree of Forgetting)0.00e+0
19
Random Data ForgettingCIFAR-100 (test)
Forgetting (Df)54.66
13
Class UnlearningCIFAR-100 (test)
Df0.00e+0
13
Random Data ForgettingCIFAR-10 (test)
Df41.28
13
Machine UnlearningCIFAR-10 (Retain)
Accuracy100
9
Random Data ForgettingTiny ImageNet (test)
Df (Forgetting)66.56
9
Knowledge DeletionCIFAR-100-KR (test)
Df71.34
9
Showing 10 of 19 rows

Other info

Follow for update