IEICE TRANSACTIONS on Information
Open Access
Energy Minimization over m-Branched Enumeration for Generalized Linear Subspace Clustering
-
Full Text Views
51
- Cite this
- Free PDF (832KB)
Summary :
In this paper, we consider the clustering problem of independent general subspaces. That is, with given data points lay near or on the union of independent low-dimensional linear subspaces, we aim to recover the subspaces and assign the corresponding label to each data point. To settle this problem, we take advantages of both greedy strategy and energy minimization strategy to propose a simple yet effective algorithm based on the assumption that an m-branched (i.e., perfect m-ary) tree which is constructed by collecting m-nearest neighbor points in each node has a high probability of containing the near-exact subspace. Specifically, at first, subspace candidates are enumerated by multiple m-branched trees. Each tree starts with a data point and grows by collecting nearest neighbors in the breadth-first search order. Then, subspace proposals are further selected from the enumeration to initialize the energy minimization algorithm. Eventually, both the proposals and the labeling result are finalized by iterative re-estimation and labeling. Experiments with both synthetic and real-world data show that the proposed method can outperform state-of-the-art methods and is practical in real application.
- Publication
- IEICE TRANSACTIONS on Information Vol.E102-D No.12 pp.2485-2492
- Publication Date
- 2019/12/01
- Publicized
- 2019/09/19
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019EDP7138
- Type of Manuscript
- PAPER
- Category
- Artificial Intelligence, Data Mining
Authors
Chao ZHANG
University of Fukui
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Chao ZHANG, "Energy Minimization over m-Branched Enumeration for Generalized Linear Subspace Clustering" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 12, pp. 2485-2492, December 2019, doi: 10.1587/transinf.2019EDP7138.
Abstract: In this paper, we consider the clustering problem of independent general subspaces. That is, with given data points lay near or on the union of independent low-dimensional linear subspaces, we aim to recover the subspaces and assign the corresponding label to each data point. To settle this problem, we take advantages of both greedy strategy and energy minimization strategy to propose a simple yet effective algorithm based on the assumption that an m-branched (i.e., perfect m-ary) tree which is constructed by collecting m-nearest neighbor points in each node has a high probability of containing the near-exact subspace. Specifically, at first, subspace candidates are enumerated by multiple m-branched trees. Each tree starts with a data point and grows by collecting nearest neighbors in the breadth-first search order. Then, subspace proposals are further selected from the enumeration to initialize the energy minimization algorithm. Eventually, both the proposals and the labeling result are finalized by iterative re-estimation and labeling. Experiments with both synthetic and real-world data show that the proposed method can outperform state-of-the-art methods and is practical in real application.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7138/_p
Copy
@ARTICLE{e102-d_12_2485,
author={Chao ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Energy Minimization over m-Branched Enumeration for Generalized Linear Subspace Clustering},
year={2019},
volume={E102-D},
number={12},
pages={2485-2492},
abstract={In this paper, we consider the clustering problem of independent general subspaces. That is, with given data points lay near or on the union of independent low-dimensional linear subspaces, we aim to recover the subspaces and assign the corresponding label to each data point. To settle this problem, we take advantages of both greedy strategy and energy minimization strategy to propose a simple yet effective algorithm based on the assumption that an m-branched (i.e., perfect m-ary) tree which is constructed by collecting m-nearest neighbor points in each node has a high probability of containing the near-exact subspace. Specifically, at first, subspace candidates are enumerated by multiple m-branched trees. Each tree starts with a data point and grows by collecting nearest neighbors in the breadth-first search order. Then, subspace proposals are further selected from the enumeration to initialize the energy minimization algorithm. Eventually, both the proposals and the labeling result are finalized by iterative re-estimation and labeling. Experiments with both synthetic and real-world data show that the proposed method can outperform state-of-the-art methods and is practical in real application.},
keywords={},
doi={10.1587/transinf.2019EDP7138},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Energy Minimization over m-Branched Enumeration for Generalized Linear Subspace Clustering
T2 - IEICE TRANSACTIONS on Information
SP - 2485
EP - 2492
AU - Chao ZHANG
PY - 2019
DO - 10.1587/transinf.2019EDP7138
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2019
AB - In this paper, we consider the clustering problem of independent general subspaces. That is, with given data points lay near or on the union of independent low-dimensional linear subspaces, we aim to recover the subspaces and assign the corresponding label to each data point. To settle this problem, we take advantages of both greedy strategy and energy minimization strategy to propose a simple yet effective algorithm based on the assumption that an m-branched (i.e., perfect m-ary) tree which is constructed by collecting m-nearest neighbor points in each node has a high probability of containing the near-exact subspace. Specifically, at first, subspace candidates are enumerated by multiple m-branched trees. Each tree starts with a data point and grows by collecting nearest neighbors in the breadth-first search order. Then, subspace proposals are further selected from the enumeration to initialize the energy minimization algorithm. Eventually, both the proposals and the labeling result are finalized by iterative re-estimation and labeling. Experiments with both synthetic and real-world data show that the proposed method can outperform state-of-the-art methods and is practical in real application.
ER -
English
