Unlearning via Sparse Representations

Vedant Shah, Frederik Träuble, Ashish Malik, Hugo Larochelle, Michael Curtis Mozer, Sanjeev Arora, Yoshua Bengio, Anirudh Goyal

Primary Area: societal considerations including fairness, safety, privacy

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.

Keywords: Unlearning, Discrete Bottlenecks, Model Editing

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a zero shot unlearning solution for neural networks which involves use of discrete bottlenecks in the model architecture

Abstract: Machine unlearning, which involves erasing knowledge about a forget set from a trained model, can prove to be costly and infeasible by existing techniques. We propose a nearly compute-free zero-shot unlearning technique based on a discrete representational bottleneck. We show that the proposed technique efficiently unlearns the forget set and incurs negligible damage to the model's performance on the rest of the data set. We evaluate the proposed technique on the problem of \textit{class unlearning} using three datasets: CIFAR-10, CIFAR-100, and LACUNA-100. We compare the proposed technique to SCRUB, a state-of-the-art approach which uses knowledge distillation for unlearning. Across all three datasets, the proposed technique performs as well as if not better than SCRUB while incurring almost no computational cost.

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.

Submission Number: 7695