Semi-supervised learning using Siamese networks

Simple item page
dc.contributor.authorSahito, Attaullahen_NZ
dc.contributor.authorFrank, Eibeen_NZ
dc.contributor.authorPfahringer, Bernharden_NZ
dc.contributor.editorLiu, Jixueen_NZ
dc.contributor.editorBailey, Jamesen_NZ
dc.coverage.spatialAdelaide, Australiaen_NZ
dc.date.accessioned2020-01-08T01:55:53Z
dc.date.available2019en_NZ
dc.date.available2020-01-08T01:55:53Z
dc.date.issued2019en_NZ
dc.description.abstractNeural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully for semi-supervised problems where small amounts of labeled instances are available along with a large number of unlabeled instances. This work explores a new training method for semi-supervised learning that is based on similarity function learning using a Siamese network to obtain a suitable embedding. The learned representations are discriminative in Euclidean space, and hence can be used for labeling unlabeled instances using a nearest-neighbor classifier. Confident predictions of unlabeled instances are used as true labels for retraining the Siamese network on the expanded training set. This process is applied iteratively. We perform an empirical study of this iterative self-training algorithm. For improving unlabeled predictions, local learning with global consistency [22] is also evaluated.
dc.format.mimetypeapplication/pdf
dc.identifier.citationSahito A., Frank E., Pfahringer B. (2019) Semi-supervised Learning Using Siamese Networks. In: Liu J., Bailey J. (eds) AI 2019: Advances in Artificial Intelligence. AI 2019. Lecture Notes in Computer Science, vol 11919. Springer, Cham
dc.identifier.doi10.1007/978-3-030-35288-2_47en_NZ
dc.identifier.isbn978-3-030-35288-2en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/13356
dc.language.isoen
dc.publisherSpringeren_NZ
dc.relation.isPartOfProceedings of 32nd Australasian Joint Conference on Advances in Artificial Intelligence (AI 2019), LNCS 11919en_NZ
dc.rightsThis is a post-peer-review, pre-copyedit version of an article published in AI 2019: Advances in Artificial Intelligence. The final authenticated version is available online at https://doi.org/10.1007/978-3-030-35288-2_47
dc.subjectcomputer scienceen_NZ
dc.subjectsemi-supervised learningen_NZ
dc.subjectSiamese networksen_NZ
dc.subjecttriplet lossen_NZ
dc.subjectLLGCen_NZ
dc.titleSemi-supervised learning using Siamese networksen_NZ
dc.typeConference Contribution
pubs.begin-page586
pubs.elements-id250080
pubs.end-page597
pubs.finish-date2019-12-05en_NZ
pubs.organisational-group/Waikato
pubs.organisational-group/Waikato/2024 PBRF
pubs.organisational-group/Waikato/DHECS
pubs.organisational-group/Waikato/DHECS/2024 PBRF - DHEC
pubs.organisational-group/Waikato/DHECS/SCMS
pubs.organisational-group/Waikato/DHECS/SCMS/2024 PBRF - SCMS
pubs.place-of-publicationCham, Switzerlanden_NZ
pubs.start-date2019-12-02en_NZ
pubs.user.infoFrank, Eibe (eibe@waikato.ac.nz)
pubs.user.infoPfahringer, Bernhard (bernhard@waikato.ac.nz)
uow.verification.statusverified
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
AI2019_042 (8).pdf
Size:
317.41 KB
Format:
Adobe Portable Document Format
Description:
Accepted version
Name: AI2019_042 (8).pdf
Size: 317.41 KB
Kind: Adobe PDF
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Research Commons Deposit Agreement 2017.pdf
Size:
188.11 KB
Format:
Adobe Portable Document Format
Description:
Name: Research Commons Deposit Agreement 2017.pdf
Size: 188.11 KB
Kind: Adobe PDF
Collections
Computing and Mathematical Sciences Papers