GEV-NN: A deep neural network architecture for class imbalance problem in binary classification

作者：

Highlights：

• GEV-NN deep learning framework is proposed for imbalanced classification.

• Gumbel distribution is used as an activation function in neural networks.

• GEV-NN outperforms state-of-the-art baseline algorithms by around 2% at most.

• GEV-NN gives a beneficial advantage to interpret variable importance.

摘要

•GEV-NN deep learning framework is proposed for imbalanced classification.•Gumbel distribution is used as an activation function in neural networks.•GEV-NN outperforms state-of-the-art baseline algorithms by around 2% at most.•GEV-NN gives a beneficial advantage to interpret variable importance.

论文关键词：Neural networks,Auto-encoder,Gumbel distribution,Imbalanced classification

论文评审过程：Received 20 September 2019, Revised 13 January 2020, Accepted 16 January 2020, Available online 18 January 2020, Version of Record 18 May 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105534