Approximate Data Deletion from Machine Learning Models

Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, James Zou
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2008-2016, 2021.

Abstract

Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU’s General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature dimension d and independent of the number of training data n. This is a significant gain over all existing methods, which all have superlinear time dependence on the dimension. We also develop a new feature-injection test to evaluate the thoroughness of data deletion from ML models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-izzo21a, title = { Approximate Data Deletion from Machine Learning Models }, author = {Izzo, Zachary and Anne Smart, Mary and Chaudhuri, Kamalika and Zou, James}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {2008--2016}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/izzo21a/izzo21a.pdf}, url = {https://proceedings.mlr.press/v130/izzo21a.html}, abstract = { Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU’s General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature dimension d and independent of the number of training data n. This is a significant gain over all existing methods, which all have superlinear time dependence on the dimension. We also develop a new feature-injection test to evaluate the thoroughness of data deletion from ML models. } }
Endnote
%0 Conference Paper %T Approximate Data Deletion from Machine Learning Models %A Zachary Izzo %A Mary Anne Smart %A Kamalika Chaudhuri %A James Zou %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-izzo21a %I PMLR %P 2008--2016 %U https://proceedings.mlr.press/v130/izzo21a.html %V 130 %X Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU’s General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature dimension d and independent of the number of training data n. This is a significant gain over all existing methods, which all have superlinear time dependence on the dimension. We also develop a new feature-injection test to evaluate the thoroughness of data deletion from ML models.
APA
Izzo, Z., Anne Smart, M., Chaudhuri, K. & Zou, J.. (2021). Approximate Data Deletion from Machine Learning Models . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:2008-2016 Available from https://proceedings.mlr.press/v130/izzo21a.html.

Related Material