Making AI Forget You: Data Deletion in Machine Learning

TL;DR

This paper addresses the challenge of efficiently deleting individual data points from trained machine learning models, proposing algorithms that significantly improve deletion efficiency while maintaining model quality.

Contribution

It introduces the first provably efficient data deletion algorithms for k-means clustering, reducing computational costs substantially compared to retraining.

Findings

Over 100X improvement in deletion efficiency across multiple datasets

Maintains comparable clustering quality to standard methods

Provides a framework for data deletion in ML models

Abstract

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.