Self-supervised Discriminative Representation Learning by Fuzzy Autoencoder

• Impact Factor:10.489
• DOI number:10.1145/1122445.1122456
• Affiliation of Author(s):西南交通大学
• Journal:ACM Transactions on Intelligent Systems and Technology
• Key Words:Additional Key Words and Phrases: autoencoders, discriminative representation learning, fuzzy clustering, self-supervised learning
• Abstract:Representation learning based on autoencoders has received great concern for its potential ability to capture valuable latent information. Conventional autoencoders (AE) pursue minimal reconstruction error, but in most machine learning tasks such as classification and clustering, the discrimination of feature representation is also important. To address this limitation, an enhanced self-supervised discriminative fuzzy autoencoder (FAE) is innovatively proposed, which focuses on exploring information within data to guide the unsupervised training process and enhancing feature discrimination in a self-supervised manner. In FAE, fuzzy membership is applied to provide a means of self-supervised, which allows FAE can not only utilize AE’s outstanding representation learning capabilities but can also transform the original data into another space with improved discrimination. Firstly, the objective function corresponding to FAE is proposed by reconstruction loss and clustering oriented loss simultaneously. Subsequently, Mini-Batch Gradient Descent (MBGD) is applied to infer the objective function and the detailed process is illustrated step by step. Finally, empirical studies on clustering tasks have demonstrated the superiority of FAE over the state-of-the-art
• Co-author:Yinghui Zhang, Zehao Liu,Tianrui Li
• First Author:Wenlu Yang
• Indexed by:Academic papers
• Correspondence Author:Hongjun Wang
• Discipline:Engineering
• First-Level Discipline:Computer Science and Technology
• Volume:Vol. 37
• Issue:No. 4, Article 111
• Page Number:19 pages
• ISSN No.:2157-6904
• Translation or Not:no