Certified Data Removal in Sum-Product Networks

TL;DR

This paper introduces UnlearnSPN, an algorithm that removes the influence of individual data points from trained sum-product networks to enhance data privacy and comply with regulations like GDPR.

Contribution

UnlearnSPN is the first method to enable data removal from sum-product networks, ensuring privacy without retraining from scratch.

Findings

Effectively removes data influence from trained models

Maintains model performance after data removal

Supports compliance with privacy regulations

Abstract

Data protection regulations like the GDPR or the California Consumer Privacy Act give users more control over the data that is collected about them. Deleting the collected data is often insufficient to guarantee data privacy since it is often used to train machine learning models, which can expose information about the training data. Thus, a guarantee that a trained model does not expose information about its training data is additionally needed. In this paper, we present UnlearnSPN -- an algorithm that removes the influence of single data points from a trained sum-product network and thereby allows fulfilling data privacy requirements on demand.