Show simple item record

dc.contributor.authorLi, Q.
dc.contributor.authorLiu, Wan-Quan
dc.contributor.authorLi, Ling
dc.contributor.authorWang, R.
dc.date.accessioned2018-06-29T12:29:13Z
dc.date.available2018-06-29T12:29:13Z
dc.date.created2018-06-29T12:08:49Z
dc.date.issued2017
dc.identifier.citationLi, Q. and Liu, W. and Li, L. and Wang, R. 2017. Towards Large Scale Spectral Problems via Diffusion Process, IEEE Catalog Number: ISBN: CFP17397-POD 978-1-5386-2840-9 2017 International Conference on Digital Image Computing: Techniques and Applications.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/69318
dc.identifier.doi10.1109/DICTA.2017.8227498
dc.description.abstract

© 2017 IEEE. Spectral methods refer to the problem of finding eigenvectors of an affinity matrix. Despite promising performance on revealing manifold structure, they are limited in its applicability to large-scale problems due to the high computational cost of eigendecomposition. Nyström method, as a classic method, seeks an approximate solution by first solving a smaller eigenproblem defined on a subset of landmarks, and then extrapolating the eigenvectors of all points through the linear combinations of landmarks. In this paper, we embed a simple yet effective diffusion process into Nyström formula so that we can utilize all data points rather than only landmarks to set up the reduced eigenproblem and estimate the out-of-sample embedding. We apply our method on both dimension reduction and spectral clustering problems. Extensive experiments show that the proposed method can reduce the approximation error with fewer landmarks and less run time.

dc.titleTowards Large Scale Spectral Problems via Diffusion Process
dc.typeConference Paper
dcterms.source.volume2017-December
dcterms.source.titleDICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications
dcterms.source.seriesDICTA 2017 - 2017 International Conference on Digital Image Computing: Techniques and Applications
dcterms.source.isbn9781538628393
dcterms.source.conferenceIEEE Catalog Number: ISBN: CFP17397-POD 978-1-5386-2840-9 2017 International Conference on Digital Image Computing: Techniques and Applications
dcterms.source.placeUSA
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Science (EECMS)
curtin.accessStatusFulltext not available


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record