A conditional variational autoencoder based self-transferred algorithm for imbalanced classification

In this paper, we propose a conditional variational autoencoder-based self-transferred (CVAE_SeTred) algorithm to solve the highly imbalanced classification problem, where the training instances of the minority classes are rare. Our method belongs to an over-sampling technique that utilizes variatio...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Knowledge-based systems 2021-04, Vol.218, p.106756, Article 106756
Hauptverfasser:	Zhao, Yudi, Hao, Kuangrong, Tang, Xue-song, Chen, Lei, Wei, Bing
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Classification Coders Datasets Domains Highly imbalanced classification Image processing Industrial applications Knowledge management Knowledge transfer Learning Over-sampling Sampling methods Training Variational autoencoders
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!