all AI news
Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images
April 22, 2024, 4:42 a.m. | Jacopo Bonato, Marco Cotogni, Luigi Sabetta
cs.LG updates on arXiv.org arxiv.org
Abstract: In this paper, we introduce Selective-distillation for Class and Architecture-agnostic unleaRning (SCAR), a novel approximate unlearning method. SCAR efficiently eliminates specific information while preserving the model's test accuracy without using a retain set, which is a key component in state-of-the-art approximate unlearning algorithms. Our approach utilizes a modified Mahalanobis distance to guide the unlearning of the feature vectors of the instances to be forgotten, aligning them to the nearest wrong class distribution. Moreover, we propose …
abstract accuracy architecture arxiv class cs.ai cs.cv cs.lg distillation distribution images information key machine novel paper performance set test type unlearning
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 23 hours ago |
arxiv.org
Learning Extrinsic Dexterity with Parameterized Manipulation Primitives
1 day, 23 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 23 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York