Sparse subspace clustering with linear subspace-neighborhood-preserving data embedding

Jwo Yuh Wu, Liang Chi Huang, Wen Hsuan Li, Hau Hsiang Chan, Chun Hung Liu, Rung Hung Gau

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Data dimensionality reduction via linear embedding is a typical approach to economizing the computational cost of machine learning systems. In the context of sparse subspace clustering (SSC), this paper proposes a two-step neighbor identification scheme using linear neighborhood-preserving embedding. In the first step, a quadratically-constrained l1 -minimization algorithm is solved for acquiring the side subspace neighborhood information, whereby a linear neighborhood-preserving embedding is designed accordingly. In the second step, a LASSO sparse regression algorithm is conducted for neighbor identification using the dimensionality-reduced data. The proposed embedding design explicitly takes into account the subspace neighborhood structure of the given data set. Computer simulations using real human face data show that the proposed embedding not only outperforms other existing dimensionality-reduction schemes but also improves the global data clustering accuracy when compared to the baseline solution without data compression.

Original languageEnglish
Title of host publication2020 IEEE 11th Sensor Array and Multichannel Signal Processing Workshop, SAM 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728119465
DOIs
StatePublished - Jun 2020
Event11th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2020 - Hangzhou, China
Duration: 8 Jun 202011 Jun 2020

Publication series

NameProceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop
Volume2020-June
ISSN (Electronic)2151-870X

Conference

Conference11th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2020
CountryChina
CityHangzhou
Period8/06/2011/06/20

Keywords

  • Compressive sensing
  • Dimensionality reduction
  • Embedding
  • Minimization -minimization
  • Sparse representation
  • Sparse subspace clustering

Fingerprint Dive into the research topics of 'Sparse subspace clustering with linear subspace-neighborhood-preserving data embedding'. Together they form a unique fingerprint.

Cite this