Anomaly detection for imbalanced datasets with deep generative models

N.R. Santos Buitrago, L.M.A. Tonnaer, V. Menkovski, Dimitrios Mavroeidis

Research output: Contribution to conferencePaperAcademic

239 Downloads (Pure)


Many important data analysis applications present with severely imbalanced datasets with respect to the target variable. A typical example is medical image analysis, where positive samples are scarce, while performance is commonly estimated against the correct detection of these positive examples. We approach this challenge by formulating the problem as anomaly detection with generative models. We train a generative model without supervision on the ‘negative’ (common) datapoints and use this model to estimate the likelihood of unseen data. A successful model allows us to detect the ‘positive’ case as low likelihood
In this position paper, we present the use of state-of-the-art deep generative models (GAN and VAE) for the estimation of a likelihood of the data. Our results show that on the one hand both GANs and VAEs are able to separate the ‘positive’ and ‘negative’ samples in the MNIST case. On the other hand, for the NLST case, neither GANs nor VAEs were able to capture the complexity of the data and discriminate anomalies at the level that this task requires. These results show that even though there are a number of successes presented in the literature for using generative models in similar applications, there remain further challenges for broad successful implementation.
Original languageEnglish
Number of pages15
Publication statusPublished - 8 Sep 2018
EventBenelearn 2018 -- Annual Machine Learning Conference of Belgium and the Netherlands - Jheronimus Academy of Data Science (JADS), 's-Hertogenbosch, Netherlands
Duration: 8 Nov 20189 Nov 2018


ConferenceBenelearn 2018 -- Annual Machine Learning Conference of Belgium and the Netherlands
Abbreviated titleBenelearn 2018
Internet address

Fingerprint Dive into the research topics of 'Anomaly detection for imbalanced datasets with deep generative models'. Together they form a unique fingerprint.

Cite this