The Brainy Student: Scalable Unlearning by Selectively Disobeying the TeacherDownload PDF

Published: 01 Feb 2023, 19:30, Last Modified: 13 Feb 2023, 23:26Submitted to ICLR 2023Readers: Everyone
Keywords: deep machine unlearning, machine unlearning, scalable unlearning
TL;DR: We propose a new approach for deep machine unlearning that breaks free of limiting assumptions made in previous work, scales significantly better and consistently outperforms previous methods across a wide range of scenarios
Abstract: Deep machine unlearning is the problem of removing the influence of a cohort of data from the weights of a trained deep model. This challenge has enjoyed increasing attention recently, motivated to the widespread use of neural networks in applications involving user data: allowing users to exercise their `right to be forgotten' necessitates an effective unlearning algorithm. Deleting data from models is also of interest in practice for removing out-of-date examples, outliers or noisy labels. However, most previous unlearning methods consider simple scenarios where a theoretical treatment is possible. Consequently, not only do their guarantees not apply to deep neural networks, but they also scale poorly. In this paper, drawing inspiration from teacher-student methods, we propose a scalable deep unlearning method that breaks free of previous limiting assumptions. Our thorough empirical investigation reveals that our approach significantly improves upon previous methods in being by far the most consistent in achieving unlearning in a wide range of scenarios, while incurring only a minimal performance degradation, if any, and being significantly more scalable than previous methods.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
15 Replies