Survey on deep learning with class imbalance

• Published in: Journal of big data Vol. 6; no. 1; pp. 1 - 54
• Main Authors: Johnson, Justin M., Khoshgoftaar, Taghi M.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 19.03.2019; Springer Nature B.V; SpringerOpen
• Subjects: Artificial neural networks; Big Data; Class imbalance; Communications Engineering; Complexity; Computational Science and Engineering; Computer Science; Computer vision; Data management; Data Mining and Knowledge Discovery; Data sampling; Database Management; Deep learning; Deep neural networks; Domains; Fraud; Information Storage and Retrieval; Machine learning; Mathematical Applications in Computer Science; Networks; Neural networks; Survey Paper; Deep learning; Big data; Deep neural networks; Class imbalance

The purpose of this study is to examine existing deep learning techniques for addressing class imbalanced data. Effective classification with imbalanced data is an important area of research, as high class imbalance is naturally inherent in many real-world applications, e.g., fraud detection and can...