Please use this identifier to cite or link to this item:
Title: Supervised representation learning with double encoding-layer autoencoder for transfer learning
Authors: Zhuang, Fuzhen
Cheng, Xiaohu
Luo, Ping
Pan, Sinno Jialin
He, Qing
Keywords: Engineering::Computer science and engineering
Issue Date: 2017
Source: Zhuang, F., Cheng, X., Luo, P., Pan, S. J., & He, Q. (2017). Supervised representation learning with double encoding-layer autoencoder for transfer learning. ACM Transactions on Intelligent Systems and Technology, 9(2), 1-17. doi:10.1145/3108257
Journal: ACM Transactions on Intelligent Systems and Technology
Abstract: Transfer learning has gained a lot of attention and interest in the past decade. One crucial research issue in transfer learning is how to find a good representation for instances of different domains such that the divergence between domains can be reduced with the new representation. Recently, deep learning has been proposed to learn more robust or higher-level features for transfer learning. In this article, we adapt the autoencoder technique to transfer learning and propose a supervised representation learning method based on double encoding-layer autoencoder. The proposed framework consists of two encoding layers: one for embedding and the other one for label encoding. In the embedding layer, the distribution distance of the embedded instances between the source and target domains is minimized in terms of KL-Divergence. In the label encoding layer, label information of the source domain is encoded using a softmax regression model. Moreover, to empirically explore why the proposed framework can work well for transfer learning, we propose a new effective measure based on autoencoder to compute the distribution distance between different domains. Experimental results show that the proposed new measure can better reflect the degree of transfer difficulty and has stronger correlation with the performance from supervised learning algorithms (e.g., Logistic Regression), compared with previous ones, such as KL-Divergence and Maximum Mean Discrepancy. Therefore, in our model, we have incorporated two distribution distance measures to minimize the difference between source and target domains in the embedding representations. Extensive experiments conducted on three real-world image datasets and one text data demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.
ISSN: 2157-6904
DOI: 10.1145/3108257
Schools: School of Computer Science and Engineering 
Rights: © 2017 Association for Computing Machinery (ACM). All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 10

Updated on May 27, 2023

Web of ScienceTM
Citations 10

Updated on May 29, 2023

Page view(s)

Updated on May 30, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.