CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification

Abstract

Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for minority class while optimizing performance for majority class. Traditional approaches to the imbalance problem include re-sampling and cost-sensitive methods. In this paper, we propose a neural network model with novel loss function, CRCEN, for imbalanced classification. Based on the weighted version of cross entropy loss, we provide a theoretical relation for model predicted probability, imbalance ratio and the weighting mechanism. To demonstrate the effectiveness of our proposed model, CRCEN is tested on several benchmark datasets and compared with baseline models.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SMOTE: Synthetic Minority Over-sampling Technique
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• A systematic study of the class imbalance problem in convolutional neural networks
• Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
• Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning