Please use this identifier to cite or link to this item:
|Title:||Scalable teacher forcing network for semi-supervised large scale data streams||Authors:||Pratama, Mahardhika
Rahayu, Dwi A. P.
|Keywords:||Engineering::Computer science and engineering||Issue Date:||2021||Source:||Pratama, M., Za'in, C., Lughofer, E., Pardede, E. & Rahayu, D. A. P. (2021). Scalable teacher forcing network for semi-supervised large scale data streams. Information Sciences, 576, 407-431. https://dx.doi.org/10.1016/j.ins.2021.06.075||Journal:||Information Sciences||Abstract:||The large-scale data stream problem refers to high-speed information flow which cannot be processed in scalable manner under a traditional computing platform. This problem also imposes expensive labelling cost making the deployment of fully supervised algorithms unfeasible. On the other hand, the problem of semi-supervised large-scale data streams is little explored in the literature because most works are designed in the traditional single-node computing environments while also being fully supervised approaches. This paper offers Weakly Supervised Scalable Teacher Forcing Network (WeScatterNet) to cope with the scarcity of labelled samples and the large-scale data streams simultaneously. WeScatterNet is crafted under distributed computing platform of Apache Spark with a data-free model fusion strategy for model compression after parallel computing stage. It features an open network structure to address the global and local drift problems while integrating a data augmentation, annotation and auto-correction (DA3) method for handling partially labelled data streams. The performance of WeScatterNet is numerically evaluated in the six large-scale data stream problems with only 25% label proportions. It shows highly competitive performance even if compared with fully supervised learners with 100% label proportions.||URI:||https://hdl.handle.net/10356/159514||ISSN:||0020-0255||DOI:||10.1016/j.ins.2021.06.075||Schools:||School of Computer Science and Engineering||Rights:||© 2021 Elsevier Inc. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||SCSE Journal Articles|
Updated on Sep 17, 2023
Web of ScienceTM
Updated on Sep 8, 2023
Updated on Sep 21, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.