Fast Machine Unlearning without Retraining through Selective Synaptic Dampening
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (11) · 12043-12051
DOI: 10.1609/aaai.v38i11.29092 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Jack Foster und 2 weiteren Autor:innen. Die Arbeit wurde bisher 96-mal zitiert (Crossref).
Abstract (Originalsprache)
Machine unlearning, the ability for a machine learning model to forget, is becoming increasingly important to comply with data privacy regulations, as well as to remove harmful, manipulated, or outdated information. The key challenge lies in forgetting specific information while protecting model performance on the remaining data. While current state-of-the-art methods perform well, they typically require some level of retraining over the retained data, in order to protect or restore model performance. This adds computational overhead and mandates that the training data remain available and accessible, which may not be feasible. In contrast, other methods employ a retrain-free paradigm, however, these approaches are prohibitively computationally expensive and do not perform on par with their retrain-based counterparts. We present Selective Synaptic Dampening (SSD), a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data. First, SSD uses the Fisher information matrix of the training and forgetting data to select parameters that are disproportionately important to the forget set. Second, SSD induces forgetting by dampening these parameters proportional to their relative importance to the forget set with respect to the wider training data. We evaluate our method against several existing unlearning methods in a range of experiments using ResNet18 and Vision Transformer. Results show that the performance of SSD is competitive with retrain-based post hoc methods, demonstrating the viability of retrain-free post hoc unlearning approaches.
Zitieren
APA
Foster, J., Schoepf, S., & Brintrup, A. (2024). Fast Machine Unlearning without Retraining through Selective Synaptic Dampening. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 12043-12051. https://doi.org/10.1609/aaai.v38i11.29092
Vancouver
Foster J, Schoepf S, Brintrup A. Fast Machine Unlearning without Retraining through Selective Synaptic Dampening. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(11):12043-12051. doi:10.1609/aaai.v38i11.29092
BibTeX
@article{Foster2024,
author = {Foster, Jack and Schoepf, Stefan and Brintrup, Alexandra},
title = {Fast Machine Unlearning without Retraining through Selective Synaptic Dampening},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {11},
pages = {12043--12051},
doi = {10.1609/aaai.v38i11.29092}
}
EUVIMED