Latent-Insensitive Autoencoders for Anomaly Detection

Muhammad S. Battikh and Artem A. Lenskiy
Additional contact information
Muhammad S. Battikh: Systems and Computer Engineering Department, Al-Azhar University, Cairo 11651, Egypt
Artem A. Lenskiy: School of Computing, The Australian National University, Canberra 2601, Australia

Mathematics, 2021, vol. 10, issue 1, 1-22

Abstract: Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabeled datasets that could be leveraged as a proxy for out-of-distribution samples. In this paper we introduce the latent-insensitive autoencoder (LIS-AE) where unlabeled data from a similar domain are utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. We provide theoretical justification for the proposed training process and loss functions along with an extensive ablation study highlighting important aspects of our model. We test our model in multiple anomaly detection settings presenting quantitative and qualitative analysis showcasing the significant performance improvement of our model for anomaly detection tasks.

Keywords: anomaly detection; autoencoders; one-class classification; principal components analysis; self-taught learning; negative examples (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/1/112/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/1/112/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2021:i:1:p:112-:d:714612

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().