Conditional Variational Autoencoder-Based Sampling

Simple item page
dc.contributor.authorKamalov, Firuz
dc.contributor.authorAli-Gombe, Adamu
dc.contributor.authorMoussa, Sherif
dc.date.accessioned2023-02-15T13:28:41Z
dc.date.available2023-02-15T13:28:41Z
dc.date.copyright© 2023
dc.date.issued2023
dc.description.abstractImbalanced data distribution implies an uneven distribution of class labels in data which can lead to classification bias in machine learning models. The present paper proposes an autoencoder-based sampling approach to balance the data. Concretely, the proposed method utilizes a conditional variational autoencoder (VAE) to learn the latent variables underpinning the distribution of minority labels. Then, the trained encoder is employed to produce new minority samples to equalize the sample distribution. The results of numerical experiments reveal the potency of the suggested technique on several datasets. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
dc.identifier.citationKamalov, F., Ali-Gombe, A., Moussa, S. (2023). Conditional Variational Autoencoder-Based Sampling. In: Fong, S., Dey, N., Joshi, A. (eds) ICT Analysis and Applications. Lecture Notes in Networks and Systems, 517, pp. 661 - 669. Springer, Singapore. https://doi.org/10.1007/978-981-19-5224-1_66
dc.identifier.isbn978-981195223-4
dc.identifier.issn23673370
dc.identifier.urihttps://hdl.handle.net/20.500.12519/743
dc.language.isoen_US
dc.publisherSpringer Science and Business Media Deutschland GmbH
dc.relationAuthors Affiliations : Kamalov, F., Department of Electrical Engineering, Canadian University Dubai, Dubai, United Arab Emirates; Ali-Gombe, A., Mintra Research, Aberdeen, United Kingdom; Moussa, S., Department of Electrical Engineering, Canadian University Dubai, Dubai, United Arab Emirates
dc.relation.ispartofseriesICT Analysis and Applications. Lecture Notes in Networks and Systems; Volume 517
dc.rightsLicense to reuse abstract has been secured from Springer Nature and Copyright Clearance Center.
dc.rights.holderCopyright : © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
dc.subjectAutoencoder
dc.subjectImbalanced data
dc.subjectSampling
dc.titleConditional Variational Autoencoder-Based Sampling
dc.typeConference Paper

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Access Instruction 743.pdf
Size:
45.1 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Department of Electrical Engineering