Meta-learning approach for variational autoencoder hyperparameter tuning
Year: 2025
Type: article
Abstract: Synthetic data generation is a promising alternative to traditional data anonymization, with Variational Autoencoders (VAEs) excelling at generating high-quality synthetic tabular datasets. However, VAE hyperparameter selection is often computationally expensive or suboptimal. We propose a meta-learning (MtL) method for hyperparameter recommendation, which achieves competitive performance to state-of-the-art Bayesian Optimization (BO) with median AUC values of 0.660 ± 0.038 (MtL) and 0.650 ± 0.041 (BO), showing no statistically significant difference. Notably, our approach reduces configuration time to under three minutes, compared to BO’s multi-hour requirement, while also enabling incremental improvements through new data integration. This combination of efficiency, adaptability, and performance establishes MtL as a practical solution for hyperparameter tuning in synthetic data generation.
DOI: 10.3897/jucs.124087
Institution: University of Trieste
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4411655403