Adaptive Compression of the Latent Space in Variational Autoencoders

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00377215" target="_blank" >RIV/68407700:21730/24:00377215 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-72332-2_7" target="_blank" >https://doi.org/10.1007/978-3-031-72332-2_7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-72332-2_7" target="_blank" >10.1007/978-3-031-72332-2_7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Adaptive Compression of the Latent Space in Variational Autoencoders

Popis výsledku v původním jazyce

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model’s sensitivity to its hyperparameters, such as the latent space size. This paper presents a simple extension of VAEs for automatically determining the optimal latent space size during the training process by gradually decreasing the latent size through neuron removal and observ ing the model performance. The proposed method is compared to the traditional and computationally costly hyperparameter grid search and is shown to be significantly faster while still achieving the best optimal dimensionality on four image datasets. Furthermore, we show that the final performance as well as the speed of our method is comparable to training on the optimal latent size from scratch, and might thus serve as a convenient substitute for example in low-resource scenarios.

Název v anglickém jazyce

Adaptive Compression of the Latent Space in Variational Autoencoders

Popis výsledku anglicky

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model’s sensitivity to its hyperparameters, such as the latent space size. This paper presents a simple extension of VAEs for automatically determining the optimal latent space size during the training process by gradually decreasing the latent size through neuron removal and observ ing the model performance. The proposed method is compared to the traditional and computationally costly hyperparameter grid search and is shown to be significantly faster while still achieving the best optimal dimensionality on four image datasets. Furthermore, we show that the final performance as well as the speed of our method is comparable to training on the optimal latent size from scratch, and might thus serve as a convenient substitute for example in low-resource scenarios.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Neural Networks and Machine Learning – ICANN 2024 33rd International Conference on Artificial Neural Networks, Lugano, Switzerland, September 17–20, 2024, Proceedings, Part IX

ISBN

978-3-031-72355-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

13

Strana od-do

89-101

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Lugano-Viganello

Datum konání akce

17. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001331868600007