Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909013078179840 |
|---|---|
| author | Senellart, Agathe Solal, Maëlys Allassonnière, Stéphanie Burgos, Ninon |
| author_facet | Senellart, Agathe Solal, Maëlys Allassonnière, Stéphanie Burgos, Ninon |
| contents | Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervised, hyperparameters are often chosen to minimize the reconstruction error on normal samples. In this paper, we reveal a trade-off between reconstruction quality and anomaly detection among $β$-VAE models. Models with constrained latent space reach higher detection metrics but lower reconstruction quality. We also assess the performance variability across random seeds and show it is linked to the distance between normal and abnormal latent distributions. From this analysis, we justify and investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE. The latter especially shows an improvement in detection while maintaining high reconstruction quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02918 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection Senellart, Agathe Solal, Maëlys Allassonnière, Stéphanie Burgos, Ninon Machine Learning Artificial Intelligence Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervised, hyperparameters are often chosen to minimize the reconstruction error on normal samples. In this paper, we reveal a trade-off between reconstruction quality and anomaly detection among $β$-VAE models. Models with constrained latent space reach higher detection metrics but lower reconstruction quality. We also assess the performance variability across random seeds and show it is linked to the distance between normal and abnormal latent distributions. From this analysis, we justify and investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE. The latter especially shows an improvement in detection while maintaining high reconstruction quality. |
| title | Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.02918 |