The Library
Bi-directional online transfer learning : a framework
Tools
Mckay, H., Griffiths, Nathan, Taylor, Phillip M., Damoulas, Theodoros and Xu, Zhou (2020) Bi-directional online transfer learning : a framework. Annals of Telecommunications, 75 . 523-547 . doi:10.1007/s12243-020-00776-1 ISSN 0003-4347.
|
PDF
WRAP-Bi-directional-online-transfer-learning-framework-Griffiths-2020.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (3544Kb) | Preview |
|
PDF
WRAP-Bi-directional-online-transfer-learning-framework-Griffiths-2020.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (10Mb) |
Official URL: https://doi.org/10.1007/s12243-020-00776-1
Abstract
Transfer learning uses knowledge learnt in source domains to aid predictions in a target domain. When source and target domains are online, they are susceptible to concept drift, which may alter the mapping of knowledge between them. Drifts in online environments can make additional information available in each domain, necessitating continuing knowledge transfer both from source to target and vice versa. To address this, we introduce the Bi-directional Online Transfer Learning (BOTL) framework, which uses knowledge learnt in each online domain to aid predictions in others. We introduce two variants of BOTL that incorporate model culling to minimise negative transfer in frameworks with high volumes of model transfer. We consider the theoretical loss of BOTL, which indicates that BOTL achieves a loss no worse than the underlying concept drift detection algorithm. We evaluate BOTL using two existing concept drift detection algorithms: RePro and ADWIN. Additionally, we present a concept drift detection algorithm, Adaptive Windowing with Proactive drift detection (AWPro), which reduces the computation and communication demands of BOTL. Empirical results are presented using two data stream generators: the drifting hyperplane emulator and the smart home heating simulator, and real-world data predicting Time To Collision (TTC) from vehicle telemetry. The evaluation shows BOTL and its variants outperform the concept drift detection strategies and the existing state-of-the-art online transfer learning technique.
Item Type: | Journal Article | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Subjects: | L Education > LB Theory and practice of education | |||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | |||||||||
Library of Congress Subject Headings (LCSH): | Internet in education, Educational technology, Web-based instruction, Education -- Computer network resources, Machine learning | |||||||||
Journal or Publication Title: | Annals of Telecommunications | |||||||||
Publisher: | Springer | |||||||||
ISSN: | 0003-4347 | |||||||||
Official Date: | October 2020 | |||||||||
Dates: |
|
|||||||||
Volume: | 75 | |||||||||
Page Range: | 523-547 | |||||||||
DOI: | 10.1007/s12243-020-00776-1 | |||||||||
Status: | Peer Reviewed | |||||||||
Publication Status: | Published | |||||||||
Access rights to Published version: | Open Access (Creative Commons) | |||||||||
Date of first compliant deposit: | 4 June 2020 | |||||||||
Date of first compliant Open Access: | 8 October 2020 | |||||||||
RIOXX Funder/Project Grant: |
|
|||||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year