Publications
Detailed Information
HexaGAN: Generative Adversarial Nets for Real World Classification
Cited 0 time in
Web of Science
Cited 9 time in Scopus
- Authors
- Issue Date
- 2019-06
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Citation
- INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, Vol.97, pp.5206-5215
- Abstract
- Most deep learning classification studies assume clean data. However, when dealing with the real world data, we encounter three problems such as 1) missing data, 2) class imbalance, and 3) missing label problems. These problems undermine the performance of a classifier. Various preprocessing techniques have been proposed to mitigate one of these problems, but an algorithm that assumes and resolves all three problems together has not been proposed yet. In this paper, we propose HexaGAN, a generative adversarial network framework that shows promising classification performance for all three problems. We interpret the three problems from a single perspective to solve them jointly. To enable this, the framework consists of six components, which interact with each other. We also devise novel loss functions corresponding to the architecture. The designed loss functions allow us to achieve state-of-the-art imputation performance, with up to a 14% improvement, and to generate high-quality class-conditional data. We evaluate the classification performance (Fl-score) of the proposed method with 20% missingness and confirm up to a 5% improvement in comparison with the performance of combinations of state-of-the-art methods.
- ISSN
- 2640-3498
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.