Mercuri, Salvatore;
Khraishi, Raad;
Okhrati, Ramin;
Batra, Devesh;
Hamill, Conor;
Ghasempour, Taha;
Nowlan, Andrew;
(2022)
An Introduction to Machine Unlearning.
Cornell University (Cornell Tech): Ithaca, NY, USA.
Preview |
Text
2209.00939v1.pdf - Other Download (854kB) | Preview |
Abstract
Removing the influence of a specified subset of training data from a machine learning model may be required to address issues such as privacy, fairness, and data quality. Retraining the model from scratch on the remaining data after removal of the subset is an effective but often infeasible option, due to its computational expense. The past few years have therefore seen several novel approaches towards efficient removal, forming the field of "machine unlearning", however, many aspects of the literature published thus far are disparate and lack consensus. In this paper, we summarise and compare seven state-of-the-art machine unlearning algorithms, consolidate definitions of core concepts used in the field, reconcile different approaches for evaluating algorithms, and discuss issues related to applying machine unlearning in practice.
Type: | Working / discussion paper |
---|---|
Title: | An Introduction to Machine Unlearning |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://doi.org/10.48550/arXiv.2209.00939 |
Language: | English |
Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
Keywords: | Machine unlearning, Exact unlearning, Approximate unlearning, Data removal, Data privacy |
UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
URI: | https://discovery.ucl.ac.uk/id/eprint/10155895 |
Archive Staff Only
View Item |