Rectified Encoder Network for High-Dimensional Imbalanced Learning

Tao ZHENG, Wei-Jie CHEN, Ivor TSANG, Xin YAO*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

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.
Original languageEnglish
Title of host publicationPRICAI 2019: Trends in Artificial Intelligence : 16th Pacific Rim International Conference on Artificial Intelligence, Cuvu, Yanuca Island, Fiji, August 26–30, 2019, Proceedings, Part II
EditorsAbhaya C. NAYAK, Alok SHARMA
PublisherSpringer
Pages684-697
Number of pages14
ISBN (Electronic)9783030299118
ISBN (Print)9783030299101
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event16th Pacific Rim International Conference on Artificial Intelligence - Cuvu, Yanuca Island, Fiji
Duration: 26 Aug 201930 Aug 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume11671
ISSN (Print)2945-9133
ISSN (Electronic)2945-9141

Conference

Conference16th Pacific Rim International Conference on Artificial Intelligence
Abbreviated titlePRICAI 2019
Country/TerritoryFiji
CityYanuca Island
Period26/08/1930/08/19

Bibliographical note

This work was supported by the National Key R&D Program of China (Grant No. 2017YFC0804003), the Program for Guangdong Introducing Innovative and Entrepreneurial Teams (Grant No. 2017ZT07X386), Shenzhen Peacock Plan (Grant No. KQTD2016112514355531), the Science and Technology Innovation Committee Foundation of Shenzhen (Grant Nos. ZDSYS201703031748284, JCYJ20180504165652917), the Program for University Key Laboratory of Guangdong Province (Grant No. 2017KSYS008), the ARC Future Fellowship ARC LP150100671, DP180100106, and National Natural Science Foundation of China (Grant Nos. 61603338, 61866010, 61703370).

Keywords

  • Characteristics extraction
  • High-dimensionality
  • Imbalanced learning
  • Representation learning

Fingerprint

Dive into the research topics of 'Rectified Encoder Network for High-Dimensional Imbalanced Learning'. Together they form a unique fingerprint.

Cite this