Rectified Encoder Network for High-Dimensional Imbalanced Learning

Zheng, Tao1,2; Chen, Wei-Jie3; Tsang, Ivor2; Yao, Xin1

10.1007/978-3-030-29911-8_53

2019

16113349

1611-3349

16th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2019

11671 LNAI

684-697

Yanuka Island, Fiji

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

Springer Verlag

Many existing works have studied the learning on imbalanced data, however, it is still very challenging to handle high-dimensional imbalanced data. One key challenge of learning on imbalanced data is that most learning models usually have a bias towards the majority and its performance will deteriorate in the presence of underrepresented data and severe class distribution skews. One solution is to synthesize the minority data to balance the class distribution, but it may lead to more overlapping, especially in the high-dimensional setting. To alleviate the above challenges, in this paper, we present a novel Rectified Encoder Network (REN) for high-dimensional imbalanced learning tasks. The main contribution is that: (1) To deal with high-dimensionality, REN encodes high-dimensional imbalanced data into low dimensional latent codes as a latent representation. (2) To obtain a discriminative representation, we introduce a Rectifier to match the latent codes with our proposed Predefined Codes, which disentangles the overlapping among classes. (3) During rectification, in the Predefined Latent Distribution, we can efficiently identify and generate informative samples to maintain the balance of class distribution, so that the minority classes will not be neglected. The experimental results on several high-dimensional and image imbalanced data sets indicate that our REN obtains good representation code for classification and visualize the reason why REN gets better performance in high-dimensional imbalanced learning.
© 2019, Springer Nature Switzerland AG.

Imbalanced learning High-dimensionality Representation learning Characteristics extraction

第一 ; 通讯

英语

EI ; CPCI-S

National Natural Science Foundation of China[61603338] ; National Natural Science Foundation of China[61703370] ; National Natural Science Foundation of China[61866010] ; Division of Arctic Sciences[ARC LP150100671] ; Division of Arctic Sciences[DP180100106] ; Shenzhen Peacock Plan[KQTD2016112514355531]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods

WOS:000558157900053

20194107504180

Artificial intelligence ; Classification (of information) ; Codes (symbols)

Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4

EV Compendex

1.Shenzhen Key Laboratory of Computational Intelligence, University Key Laboratory of Evolving Intelligent Systems of Guangdong Province, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen; 518055, China
2.Centre for Artificial Intelligence (CAI), University of Technology Sydney, Ultimo, Australia
3.Zhijiang College, Zhejiang University of Technology, Hangzhou Shi, China

Zheng, Tao,Chen, Wei-Jie,Tsang, Ivor,et al. Rectified Encoder Network for High-Dimensional Imbalanced Learning[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:Springer Verlag,2019:684-697.