A robust variational autoencoder using beta divergence

The presence of outliers can severely degrade learned representations and performance of deep learning methods and hence disproportionately affect the training process, leading to incorrect conclusions about the data. For example, anomaly detection using deep generative models is typically only poss...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Knowledge-based systems Ročník 238; s. 107886
Hlavní autori: Akrami, Haleh, Joshi, Anand A., Li, Jian, Aydöre, Sergül, Leahy, Richard M.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Netherlands Elsevier B.V 28.02.2022
Elsevier Science Ltd
Predmet:
Anomalies
Brain damage
Data
Data analysis
Deep learning
Lesions
Lower bounds
Neuroimaging
Outlier
Outliers (statistics)
Robust anomaly detection
Robust control
Robustness
RVAE
Statistics
Training
VAE
β divergence
Outlier
β divergence
Robust anomaly detection
VAE
RVAE
β divergence
ISSN:0950-7051, 1872-7409
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The presence of outliers can severely degrade learned representations and performance of deep learning methods and hence disproportionately affect the training process, leading to incorrect conclusions about the data. For example, anomaly detection using deep generative models is typically only possible when similar anomalies (or outliers) are not present in the training data. Here we focus on variational autoencoders (VAEs). While the VAE is a popular framework for anomaly detection tasks, we observe that the VAE is unable to detect outliers when the training data contains anomalies that have the same distribution as those in test data. In this paper we focus on robustness to outliers in training data in VAE settings using concepts from robust statistics. We propose a variational lower bound that leads to a robust VAE model that has the same computational complexity as the standard VAE and contains a single automatically-adjusted tuning parameter to control the degree of robustness. We present mathematical formulations for robust variational autoencoders (RVAEs) for Bernoulli, Gaussian and categorical variables. The RVAE model is based on beta-divergence rather than the standard Kullback–Leibler (KL) divergence. We demonstrate the performance of our proposed β-divergence-based autoencoder for a variety of image and categorical datasets showing improved robustness to outliers both qualitatively and quantitatively. We also illustrate the use of our robust VAE for detection of lesions in brain images, formulated as an anomaly detection task. Finally, we suggest a method to tune the hyperparameter of RVAE which makes our model completely unsupervised.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2021.107886