Addressing the multi-label imbalance for neural networks: An approach based on stratified mini-batches
Authors:
- Dunlu PengDPDunlu Peng
- Tianfei GuTGTianfei Gu
- Xue HuXHXue Hu
- Cong LiuCLCong Liu
- 1 May 2021
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 435, 91-102
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61772342)
- National Natural Science Foundation of China (61703278)
This publication has 44 references indexed in Scilit:
- Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approachesKnowledge-Based Systems, 2013
- Managing Imbalanced Data Sets in Multi-label Problems: A Case Study with the SMOTE Algorithm2013
- A First Approach to Deal with Imbalance in Multi-label Datasets2013
- Inverse random under sampling for class imbalance problem and its application to multi-label classificationPattern Recognition, 2012
- Multilabel classification using heterogeneous ensemble of multi-label classifiersPattern Recognition Letters, 2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Random k-Labelsets: An Ensemble Method for Multilabel Classification2007
- ML-KNN: A lazy learning approach to multi-label learningPattern Recognition, 2007
- Learning multi-label scene classificationPattern Recognition, 2004
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991