Can We Find Strong Lottery Tickets in Generative Models?

4Citations
Citations of this article
20Readers
Mendeley users who have this article in their library.

Abstract

Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerstone of model compression for reducing the costs of computation and memory. Unfortunately, pruning a generative model has not been extensively explored, and all existing pruning algorithms suffer from excessive weight-training costs, performance degradation, limited generalizability, or complicated training. To address these problems, we propose to find a strong lottery ticket via moment-matching scores. Our experimental results show that the discovered subnetwork can perform similarly or better than the trained dense model even when only 10% of the weights remain. To the best of our knowledge, we are the first to show the existence of strong lottery tickets in generative models and provide an algorithm to find it stably. Our code and supplementary materials are publicly available at https://lait-cvlab.github.io/SLT-in-Generative-Models/.

Cite

CITATION STYLE

APA

Yeo, S., Jang, Y., Sohn, J. Y., Han, D., & Yoo, J. (2023). Can We Find Strong Lottery Tickets in Generative Models? In Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023 (Vol. 37, pp. 3267–3275). AAAI Press. https://doi.org/10.1609/aaai.v37i3.25433

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free