Survey on deep learning with class imbalance

被引:1630
作者
Johnson, Justin M. [1 ]
Khoshgoftaar, Taghi M. [1 ]
机构
[1] Florida Atlantic Univ, 777 Glades Rd, Boca Raton, FL 33431 USA
关键词
Deep learning; Deep neural networks; Class imbalance; Big data; CLASSIFICATION; MACHINE; ALGORITHM; NETWORKS; FRAUD; SMOTE;
D O I
10.1186/s40537-019-0192-5
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
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 cancer detection. Moreover, highly imbalanced data poses added difficulty, as most learners will exhibit bias towards the majority class, and in extreme cases, may ignore the minority class altogether. Class imbalance has been studied thoroughly over the last two decades using traditional machine learning models, i.e. non-deep learning. Despite recent advances in deep learning, along with its increasing popularity, very little empirical work in the area of deep learning with class imbalance exists. Having achieved record-breaking performance results in several complex domains, investigating the use of deep neural networks for problems containing high levels of class imbalance is of great interest. Available studies regarding class imbalance and deep learning are surveyed in order to better understand the efficacy of deep learning when applied to class imbalanced data. This survey discusses the implementation details and experimental results for each study, and offers additional insight into their strengths and weaknesses. Several areas of focus include: data complexity, architectures tested, performance interpretation, ease of use, big data application, and generalization to other domains. We have found that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered. Several traditional methods for class imbalance, e.g. data sampling and cost-sensitive learning, prove to be applicable in deep learning, while more advanced methods that exploit neural network feature learning abilities show promising results. The survey concludes with a discussion that highlights various gaps in deep learning from class imbalanced data for the purpose of guiding future research.
引用
收藏
页数:54
相关论文
共 132 条
[61]  
Jo T., 2004, ACM SIGKDD Explorations Newsletter, V6, P40, DOI DOI 10.1145/1007730.1007737
[62]  
Kawaguchi Kenji, 2016, Advances in Neural Information Processing Systems NeurIPS, P586
[63]   Cost-Sensitive Learning of Deep Feature Representations From Imbalanced Data [J].
Khan, Salman H. ;
Hayat, Munawar ;
Bennamoun, Mohammed ;
Sohel, Ferdous A. ;
Togneri, Roberto .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (08) :3573-3587
[64]  
Kotsiantis SB, 2007, INFORM-J COMPUT INFO, V31, P249
[65]   Automatic grading of human blastocysts from time-lapse imaging [J].
Kragh, Mikkel F. ;
Rimestad, Jens ;
Berntsen, Jorgen ;
Karstoft, Henrik .
COMPUTERS IN BIOLOGY AND MEDICINE, 2019, 115
[66]   Learning from imbalanced data: open challenges and future directions [J].
Krawczyk B. .
Progress in Artificial Intelligence, 2016, 5 (04) :221-232
[67]  
Krizhevsky A., CIFAR-100
[68]  
Krizhevsky A., CIFAR-10
[69]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[70]   Machine learning for the detection of oil spills in satellite radar images [J].
Kubat, M ;
Holte, RC ;
Matwin, S .
MACHINE LEARNING, 1998, 30 (2-3) :195-215