Robustly Train Normalizing Flows via KL Divergence Regularization
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (13) · 15047-15055
DOI: 10.1609/aaai.v38i13.29426 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Kun Song und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
In this paper, we find that the training of Normalizing Flows (NFs) are easily affected by the outliers and a small number (or high dimensionality) of training samples. To solve this problem, we propose a Kullback–Leibler (KL) divergence regularization on the Jacobian matrix of NFs. We prove that such regularization is equivalent to adding a set of samples whose covariance matrix is the identity matrix to the training set. Thus, it reduces the negative influence of the outliers and the small sample number on the estimation of the covariance matrix, simultaneously. Therefore, our regularization makes the training of NFs robust. Ultimately, we evaluate the performance of NFs on out-of-distribution (OoD) detection tasks. The excellent results obtained demonstrate the effectiveness of the proposed regularization term. For example, with the help of the proposed regularization, the OoD detection score increases at most 30% compared with the one without the regularization.
Zitieren
APA
Song, K., Solozabal, R., Li, H., Takáč, M., Ren, L., & Karray, F. (2024). Robustly Train Normalizing Flows via KL Divergence Regularization. Proceedings of the AAAI Conference on Artificial Intelligence, 38(13), 15047-15055. https://doi.org/10.1609/aaai.v38i13.29426
Vancouver
Song K, Solozabal R, Li H, Takáč M, Ren L, Karray F. Robustly Train Normalizing Flows via KL Divergence Regularization. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(13):15047-15055. doi:10.1609/aaai.v38i13.29426
BibTeX
@article{Song2024,
author = {Song, Kun and Solozabal, Ruben and Li, Hao and Takáč, Martin and Ren, Lu and Karray, Fakhri},
title = {Robustly Train Normalizing Flows via KL Divergence Regularization},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {13},
pages = {15047--15055},
doi = {10.1609/aaai.v38i13.29426}
}
EUVIMED