A buffered online transfer learning algorithm with multi-layer network
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
A buffered online transfer learning algorithm with multi-layer network. / Kang, Zhongfeng; Yang, Bo; Nielsen, Mads; Deng, Lihui; Yang, Shantian.
In: Neurocomputing, Vol. 488, 2022, p. 581-597.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - A buffered online transfer learning algorithm with multi-layer network
AU - Kang, Zhongfeng
AU - Yang, Bo
AU - Nielsen, Mads
AU - Deng, Lihui
AU - Yang, Shantian
N1 - Publisher Copyright: © 2021 Elsevier B.V.
PY - 2022
Y1 - 2022
N2 - Online transfer learning (OTL) has attracted much attention in recent years. It is designed to handle the transfer learning tasks, where the data of the target domain isn't available in advance but may arrive in an online manner, which may be a more realistic scenario in practice. However, there typically are two limitations of existing OTL algorithms. 1) Existing OTL algorithms are based on shallow online learning models (SOLMs), e.g., linear or kernel models. Due to this limitation of SOLMs they cannot effectively learn complex nonlinear functions in complicated application and the OTL algorithms based on SOLMs cannot either. 2) Existing algorithms only utilize the latest arrived instance to adjust the model. In this way, the previously arrived instances are not utilized. It may be better to utilize the previously arrived instances as well. In this paper, to overcome the abovementioned two limitations, a buffered online transfer learning (BOTL) algorithm is proposed. In the proposed BOTL algorithm, the learner is designed as a deep learning model, referred to as Online Hedge Neural Network (OHNN). In order to enable the OHNN to be effectively learned in an online manner, we propose a buffered online learning framework that utilizes several previously arrived instances to assist learning. Further, to enhance the performance of the OHNN, a model learned in the source domain is transferred to the target domain. The regret bound of the proposed BOTL algorithm is analyzed theoretically. Experimental results on realistic datasets illustrate that the proposed BOTL algorithm can achieve lower mistake rate than the algorithms compared.
AB - Online transfer learning (OTL) has attracted much attention in recent years. It is designed to handle the transfer learning tasks, where the data of the target domain isn't available in advance but may arrive in an online manner, which may be a more realistic scenario in practice. However, there typically are two limitations of existing OTL algorithms. 1) Existing OTL algorithms are based on shallow online learning models (SOLMs), e.g., linear or kernel models. Due to this limitation of SOLMs they cannot effectively learn complex nonlinear functions in complicated application and the OTL algorithms based on SOLMs cannot either. 2) Existing algorithms only utilize the latest arrived instance to adjust the model. In this way, the previously arrived instances are not utilized. It may be better to utilize the previously arrived instances as well. In this paper, to overcome the abovementioned two limitations, a buffered online transfer learning (BOTL) algorithm is proposed. In the proposed BOTL algorithm, the learner is designed as a deep learning model, referred to as Online Hedge Neural Network (OHNN). In order to enable the OHNN to be effectively learned in an online manner, we propose a buffered online learning framework that utilizes several previously arrived instances to assist learning. Further, to enhance the performance of the OHNN, a model learned in the source domain is transferred to the target domain. The regret bound of the proposed BOTL algorithm is analyzed theoretically. Experimental results on realistic datasets illustrate that the proposed BOTL algorithm can achieve lower mistake rate than the algorithms compared.
KW - Deep learning
KW - Multi-layer neural network
KW - Online learning
KW - Online transfer learning
KW - Transfer learning
U2 - 10.1016/j.neucom.2021.11.066
DO - 10.1016/j.neucom.2021.11.066
M3 - Journal article
AN - SCOPUS:85120776938
VL - 488
SP - 581
EP - 597
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
ER -
ID: 291543669