Constrained clustering - Revision history

Marsdancer: Cite COP K-means paper as the original paper describing must-link and cannot-link constraints.

2025-03-27T16:49:58Z

Cite COP K-means paper as the original paper describing must-link and cannot-link constraints.

@@ Line 1: / Line 1: @@
 {{Short description|Class of semi-supervised learning algorithms}}
-In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[data clustering]] algorithm. A cluster in which the members conform to all must-link and cannot-link constraints is called a '''chunklet'''.
+In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[data clustering]] algorithm.<ref name="copkmeans">{{Cite conference
 == Types of constraints ==
@@ Line 24: / Line 33: @@
 ==Examples==
 Examples of constrained clustering algorithms include:
-* COP K-means <ref>{{Cite conference
+* COP K-means <ref name="copkmeans"/>
 * PCKmeans (Pairwise Constrained K-means) <ref>{{Cite conference |last=Basu |first=Sugato |last2=Banerjee |first2=Arindam |last3=Mooney |first3=Raymond J. |author-link3=Raymond J. Mooney |date=April 2004 |title=Active Semi-Supervision for Pairwise Constrained Clustering |url=https://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf |conference=Proceedings of the 2004 SIAM International Conference on Data Mining |pages=333–344}}</ref>
 * CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference

Marsdancer: /* Add link to Kiri Wagstaff's page */

2025-03-21T05:43:42Z

Add link to Kiri Wagstaff's page

← Previous revision		Revision as of 05:43, 21 March 2025
Line 25:		Line 25:
	Examples of constrained clustering algorithms include:		Examples of constrained clustering algorithms include:
	* COP K-means <ref>{{Cite conference		* COP K-means <ref>{{Cite conference
	\| first1 = K. \|last1=Wagstaff		\| first1 = K. \|last1=Wagstaff \| author1-link = Kiri Wagstaff
	\| first2 = C. \|last2=Cardie \| author2-link = Claire Cardie		\| first2 = C. \|last2=Cardie \| author2-link = Claire Cardie
	\| first3 = S. \|last3=Rogers		\| first3 = S. \|last3=Rogers

Sodium hypobromite: /* References */ Expanded bare PDF URL

2025-01-18T05:57:13Z

References: Expanded bare PDF URL

← Previous revision		Revision as of 05:57, 18 January 2025
Line 34:		Line 34:
	\| pages = 577–584		\| pages = 577–584
	}}</ref>		}}</ref>
	* PCKmeans (Pairwise Constrained K-means) <ref>~~http~~://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf ~~{{Bare~~ ~~URL~~ ~~PDF~~\|~~date~~=~~March 2022~~}}</ref>		* PCKmeans (Pairwise Constrained K-means) <ref>{{Cite conference \|last=Basu \|first=Sugato \|last2=Banerjee \|first2=Arindam \|last3=Mooney \|first3=Raymond J. \|author-link3=Raymond J. Mooney \|date=April 2004 \|title=Active Semi-Supervision for Pairwise Constrained Clustering \|url=https://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf \|conference=Proceedings of the 2004 SIAM International Conference on Data Mining \|pages=333–344}}</ref>
	* CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference		* CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference
	\| first1 = R. C. \|last1=de Amorim		\| first1 = R. C. \|last1=de Amorim

SimLibrarian at 23:29, 8 December 2023

2023-12-08T23:29:37Z

← Previous revision		Revision as of 23:29, 8 December 2023
Line 1:		Line 1:
			{{Short description\|Class of semi-supervised learning algorithms}}
	In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[data clustering]] algorithm. A cluster in which the members conform to all must-link and cannot-link constraints is called a '''chunklet'''.		In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[data clustering]] algorithm. A cluster in which the members conform to all must-link and cannot-link constraints is called a '''chunklet'''.

MewTheEditor: Moved second half of the lead to a section.

2022-06-08T13:31:31Z

Moved second half of the lead to a section.

← Previous revision		Revision as of 13:31, 8 June 2022
Line 1:		Line 1:
	In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[~~Data~~ clustering]] algorithm. Both a must-link and a cannot-link constraint define a relationship between two data instances. A must-link constraint is used to specify that the two instances in the must-link relation should be associated with the same cluster. A cannot-link constraint is used to specify that the two instances in the cannot-link relation should ''not'' be associated with the same cluster. ~~These sets of constraints acts as a guide for which a constrained clustering algorithm will attempt to find clusters in a data set which satisfy the specified must-link and cannot-link constraints.~~ Some constrained clustering algorithms will abort if no such clustering exists which satisfies the specified constraints. Others will try to minimize the amount of constraint violation should it be impossible to find a clustering which satisfies the constraints. Constraints could also be used to guide the selection of a clustering model among several possible solutions.<ref name="pourrajabi">{{Cite conference		In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[data clustering]] algorithm. A cluster in which the members conform to all must-link and cannot-link constraints is called a '''chunklet'''.

			== Types of constraints ==
			Both a must-link and a cannot-link constraint define a relationship between two data instances. Together, the sets of these constraints act as a guide for which a constrained clustering algorithm will attempt to find chunklets (clusters in the dataset which satisfy the specified constraints).

			* A ''must-link constraint'' is used to specify that the two instances in the must-link relation should be associated with the same cluster.
			* A ''cannot-link constraint'' is used to specify that the two instances in the cannot-link relation should ''not'' be associated with the same cluster.

			Some constrained clustering algorithms will abort if no such clustering exists which satisfies the specified constraints. Others will try to minimize the amount of constraint violation should it be impossible to find a clustering which satisfies the constraints. Constraints could also be used to guide the selection of a clustering model among several possible solutions.<ref name="pourrajabi">{{Cite conference
	\| first1 = M. \| last1 = Pourrajabi		\| first1 = M. \| last1 = Pourrajabi
	\| first2 = D. \| last2 = Moulavi		\| first2 = D. \| last2 = Moulavi
Line 12:		Line 20:
	\| doi = 10.5441/002/edbt.2014.31		\| doi = 10.5441/002/edbt.2014.31
	}}</ref>		}}</ref>

	A cluster in which the members conform to all must-link and cannot-link constraints is called a '''chunklet'''.

	==Examples==		==Examples==

BrownHairedGirl: tag with {{Bare URL PDF}}

2022-03-14T05:52:49Z

tag with {{Bare URL PDF}}

← Previous revision		Revision as of 05:52, 14 March 2022
Line 1:		Line 1:
	In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[Data clustering]] algorithm. Both a must-link and a cannot-link constraint define a relationship between two data instances. A must-link constraint is used to specify that the two instances in the must-link relation should be associated with the same cluster. A cannot-link constraint is used to specify that the two instances in the cannot-link relation should ''not'' be associated with the same cluster. These sets of constraints acts as a guide for which a constrained clustering algorithm will attempt to find clusters in a data set which satisfy the specified must-link and cannot-link constraints. Some constrained clustering algorithms will abort if no such clustering exists which satisfies the specified constraints. Others will try to minimize the amount of constraint violation should it be impossible to find a clustering which satisfies the constraints. Constraints could also be used to guide the selection of a clustering model among several possible solutions. <ref name="pourrajabi">{{Cite conference		In [[computer science]], '''constrained clustering''' is a class of [[semi-supervised learning]] algorithms. Typically, constrained clustering incorporates either a set of must-link constraints, cannot-link constraints, or both, with a [[Data clustering]] algorithm. Both a must-link and a cannot-link constraint define a relationship between two data instances. A must-link constraint is used to specify that the two instances in the must-link relation should be associated with the same cluster. A cannot-link constraint is used to specify that the two instances in the cannot-link relation should ''not'' be associated with the same cluster. These sets of constraints acts as a guide for which a constrained clustering algorithm will attempt to find clusters in a data set which satisfy the specified must-link and cannot-link constraints. Some constrained clustering algorithms will abort if no such clustering exists which satisfies the specified constraints. Others will try to minimize the amount of constraint violation should it be impossible to find a clustering which satisfies the constraints. Constraints could also be used to guide the selection of a clustering model among several possible solutions.<ref name="pourrajabi">{{Cite conference
	\| first1 = M. \| last1 = Pourrajabi		\| first1 = M. \| last1 = Pourrajabi
	\| first2 = D. \| last2 = Moulavi		\| first2 = D. \| last2 = Moulavi
Line 27:		Line 27:
	\| pages = 577–584		\| pages = 577–584
	}}</ref>		}}</ref>
	* PCKmeans (Pairwise Constrained K-means) <ref>http://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf</ref>		* PCKmeans (Pairwise Constrained K-means) <ref>http://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf {{Bare URL PDF\|date=March 2022}}</ref>
	* CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference		* CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference
	\| first1 = R. C. \|last1=de Amorim		\| first1 = R. C. \|last1=de Amorim
Line 41:		Line 41:
	{{Reflist\|1}}		{{Reflist\|1}}

		⚫	[[Category:Cluster analysis algorithms]]
		⚫	[[Category:Cluster analysis]]


	{{comp-sci-stub}}		{{comp-sci-stub}}
⚫	[[Category:Cluster analysis algorithms]]
⚫	[[Category:Cluster analysis]]

Monkbot: Task 18 (cosmetic): eval 3 templates: hyphenate params (3×);

2021-01-13T14:52:21Z

Task 18 (cosmetic): eval 3 templates: hyphenate params (3×);

← Previous revision		Revision as of 14:52, 13 January 2021
Line 8:		Line 8:
	\| year = 2014		\| year = 2014
	\| title = Model Selection for Semi-Supervised Clustering		\| title = Model Selection for Semi-Supervised Clustering
	\| ~~booktitle~~ = Proceedings of the 17th International Conference on Extending Database Technology (EDBT)		\| book-title = Proceedings of the 17th International Conference on Extending Database Technology (EDBT)
	\| pages = 331–342		\| pages = 331–342
	\| doi = 10.5441/002/edbt.2014.31		\| doi = 10.5441/002/edbt.2014.31
Line 24:		Line 24:
	\| year = 2001		\| year = 2001
	\| title = Constrained K-means Clustering with Background Knowledge		\| title = Constrained K-means Clustering with Background Knowledge
	\| ~~booktitle~~ = Proceedings of the Eighteenth International Conference on Machine Learning.		\| book-title = Proceedings of the Eighteenth International Conference on Machine Learning.
	\| pages = 577–584		\| pages = 577–584
	}}</ref>		}}</ref>
Line 32:		Line 32:
	\| year = 2012		\| year = 2012
	\| title = Constrained Clustering with Minkowski Weighted K-Means		\| title = Constrained Clustering with Minkowski Weighted K-Means
	\| ~~booktitle~~ = Proceedings of the 13th IEEE International Symposium on Computational Intelligence and Informatics		\| book-title = Proceedings of the 13th IEEE International Symposium on Computational Intelligence and Informatics
	\| pages = 13–17		\| pages = 13–17
	\| doi=10.1109/CINTI.2012.6496753		\| doi=10.1109/CINTI.2012.6496753

David Eppstein: Claire Cardie

2019-12-12T05:59:56Z

Claire Cardie

← Previous revision		Revision as of 05:59, 12 December 2019
Line 19:		Line 19:
	* COP K-means <ref>{{Cite conference		* COP K-means <ref>{{Cite conference
	\| first1 = K. \|last1=Wagstaff		\| first1 = K. \|last1=Wagstaff
	\| first2 = C. \|last2=Cardie		\| first2 = C. \|last2=Cardie \| author2-link = Claire Cardie
	\| first3 = S. \|last3=Rogers		\| first3 = S. \|last3=Rogers
	\| first4 = S. \|last4=Schrödl		\| first4 = S. \|last4=Schrödl

Citation bot: Alter: booktitle. | You can use this bot yourself. Report bugs here.| Activated by User:Nemo bis | via #UCB_webform

2019-12-10T16:40:57Z

Alter: booktitle. | You can use this bot yourself. Report bugs here.| Activated by User:Nemo bis | via #UCB_webform

← Previous revision		Revision as of 16:40, 10 December 2019
Line 8:		Line 8:
	\| year = 2014		\| year = 2014
	\| title = Model Selection for Semi-Supervised Clustering		\| title = Model Selection for Semi-Supervised Clustering
	\| booktitle = Proceedings of the 17th International Conference on Extending Database Technology (EDBT),		\| booktitle = Proceedings of the 17th International Conference on Extending Database Technology (EDBT)
	\| pages = 331–342		\| pages = 331–342
	\| doi = 10.5441/002/edbt.2014.31		\| doi = 10.5441/002/edbt.2014.31

Owl-syme: /* Examples */ expand abbreviations

2018-04-02T09:46:27Z

Examples: expand abbreviations

← Previous revision		Revision as of 09:46, 2 April 2018
Line 27:		Line 27:
	\| pages = 577–584		\| pages = 577–584
	}}</ref>		}}</ref>
	* PCKmeans <ref>http://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf</ref>		* PCKmeans (Pairwise Constrained K-means) <ref>http://www.cs.utexas.edu/~ml/papers/semi-sdm-04.pdf</ref>
	* CMWK-Means <ref>{{Cite conference		* CMWK-Means (Constrained Minkowski Weighted K-Means) <ref>{{Cite conference
	\| first1 = R. C. \|last1=de Amorim		\| first1 = R. C. \|last1=de Amorim
	\| year = 2012		\| year = 2012

← Previous revision		Revision as of 05:59, 12 December 2019
Line 19:		Line 19:
	* COP K-means <ref>{{Cite conference		* COP K-means <ref>{{Cite conference
	\| first1 = K. \|last1=Wagstaff		\| first1 = K. \|last1=Wagstaff
	\| first2 = C. \|last2=Cardie		\| first2 = C. \|last2=Cardie \| author2-link = Claire Cardie
	\| first3 = S. \|last3=Rogers		\| first3 = S. \|last3=Rogers
	\| first4 = S. \|last4=Schrödl		\| first4 = S. \|last4=Schrödl