Label propagation algorithm - Revision history

R88D88: Link to Weak supervision article

2024-12-28T10:14:14Z

Link to Weak supervision article

← Previous revision		Revision as of 10:14, 28 December 2024
Line 3:		Line 3:
	{{technical\|date=June 2015}}		{{technical\|date=June 2015}}
	}}		}}
	'''Label propagation''' is a semi-supervised [[machine learning]] ~~algorithm~~ that assigns labels to previously unlabeled data points. At the start of the algorithm, a (generally small) subset of the data points have labels (or classifications). These labels are propagated to the unlabeled points throughout the course of the algorithm.<ref>{{cite journal\|last1=Zhu\|first1=Xiaojin\|title=Learning From Labeled and Unlabeled Data With Label Propagation\|year=2002\|citeseerx=10.1.1.14.3864}}</ref>		'''Label propagation''' is a [[Weak supervision\|semi-supervised]] algorithm in [[machine learning]] that assigns labels to previously unlabeled data points. At the start of the algorithm, a (generally small) subset of the data points have labels (or classifications). These labels are propagated to the unlabeled points throughout the course of the algorithm.<ref>{{cite journal\|last1=Zhu\|first1=Xiaojin\|title=Learning From Labeled and Unlabeled Data With Label Propagation\|year=2002\|citeseerx=10.1.1.14.3864}}</ref>

	Within [[complex networks]], real networks tend to have [[community structure]]. Label propagation is an algorithm <ref name="raghavan-albert-kumara2007">U.N.Raghavan – R. Albert – S. Kumara [https://arxiv.org/abs/0709.2938 "Near linear time algorithm to detect community structures in large-scale networks"], 2007</ref> for finding communities. In comparison with other algorithms<ref>M. E. J. Newman, [http://www-personal.umich.edu/~mejn/papers/epjb.pdf "Detecting community structure in networks"], 2004</ref> label propagation has advantages in its running time and amount of a priori information needed about the network structure (no parameter is required to be known beforehand). The disadvantage is that it produces no unique solution, but an aggregate of many solutions.		Within [[complex networks]], real networks tend to have [[community structure]]. Label propagation is an algorithm <ref name="raghavan-albert-kumara2007">U.N.Raghavan – R. Albert – S. Kumara [https://arxiv.org/abs/0709.2938 "Near linear time algorithm to detect community structures in large-scale networks"], 2007</ref> for finding communities. In comparison with other algorithms<ref>M. E. J. Newman, [http://www-personal.umich.edu/~mejn/papers/epjb.pdf "Detecting community structure in networks"], 2004</ref> label propagation has advantages in its running time and amount of a priori information needed about the network structure (no parameter is required to be known beforehand). The disadvantage is that it produces no unique solution, but an aggregate of many solutions.

Citation bot: Altered template type. Added class. Removed URL that duplicated identifier. Removed parameters. | Use this bot. Report bugs. | Suggested by Jay8g | #UCB_toolbar

2024-10-17T04:45:48Z

Altered template type. Added class. Removed URL that duplicated identifier. Removed parameters. | Use this bot. Report bugs. | Suggested by Jay8g | #UCB_toolbar

← Previous revision		Revision as of 04:45, 17 October 2024
Line 24:		Line 24:

	==Application in text classification and machine learning==		==Application in text classification and machine learning==
	Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite ~~journal~~ \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|~~journal~~=~~arXiv~~ \|eprint=2410.11355 \|year=2024 ~~\|url=https://arxiv.org/abs/2410.11355~~}}</ref>		Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite arXiv \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|class=cs.LG \|eprint=2410.11355 \|year=2024 }}</ref>

	==Multiple community structure==		==Multiple community structure==

76.20.252.182 at 14:20, 16 October 2024

2024-10-16T14:20:45Z

← Previous revision		Revision as of 14:20, 16 October 2024
Line 22:		Line 22:

	5. If every node has a label that the maximum number of their neighbours have, then stop the algorithm. Else, set t = t + 1 and go to (3).		5. If every node has a label that the maximum number of their neighbours have, then stop the algorithm. Else, set t = t + 1 and go to (3).

			==Application in text classification and machine learning==
			Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite journal \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|journal=arXiv \|eprint=2410.11355 \|year=2024 \|url=https://arxiv.org/abs/2410.11355}}</ref>

	==Multiple community structure==		==Multiple community structure==

Cooldudeseven7: Reverting edit(s) by 76.20.252.182 (talk) to rev. 1179227513 by JoeNMLC: Reverting good faith edits: References seem broken (UV 0.1.6)

2024-10-16T14:17:44Z

Reverting edit(s) by 76.20.252.182 (talk) to rev. 1179227513 by JoeNMLC: Reverting good faith edits: References seem broken (UV 0.1.6)

← Previous revision		Revision as of 14:17, 16 October 2024
Line 22:		Line 22:

	5. If every node has a label that the maximum number of their neighbours have, then stop the algorithm. Else, set t = t + 1 and go to (3).		5. If every node has a label that the maximum number of their neighbours have, then stop the algorithm. Else, set t = t + 1 and go to (3).


	==Application in text classification and machine learning==
	Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite arxiv \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|year=2024 \|url=https://arxiv.org/abs/2410.11355}}</ref>





	==Multiple community structure==		==Multiple community structure==
Line 37:		Line 29:
	==References==		==References==
	{{reflist}}		{{reflist}}

	<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->		<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->
	*		*
Line 43:		Line 34:
	*		*
	*		*



	==External links==		==External links==

76.20.252.182 at 14:16, 16 October 2024

2024-10-16T14:16:25Z

← Previous revision		Revision as of 14:16, 16 October 2024
Line 25:		Line 25:

	==Application in text classification and machine learning==		==Application in text classification and machine learning==
	Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite arxiv \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning ~~\|eprint=2410.11355 \|archivePrefix=arXiv~~ \|year=2024 \|url=https://arxiv.org/abs/2410.11355}}</ref>		Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite arxiv \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|year=2024 \|url=https://arxiv.org/abs/2410.11355}}</ref>

76.20.252.182 at 14:12, 16 October 2024

2024-10-16T14:12:37Z

← Previous revision		Revision as of 14:12, 16 October 2024
Line 25:		Line 25:

	==Application in text classification and machine learning==		==Application in text classification and machine learning==
	Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024"/>		Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024">{{cite arxiv \|last1=Jafarlou \|first1=Minoo \|last2=Kubek \|first2=Mario M. \|title=Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning \|eprint=2410.11355 \|archivePrefix=arXiv \|year=2024 \|url=https://arxiv.org/abs/2410.11355}}</ref>

76.20.252.182 at 14:09, 16 October 2024

2024-10-16T14:09:08Z

← Previous revision		Revision as of 14:09, 16 October 2024
Line 25:		Line 25:

	==Application in text classification and machine learning==		==Application in text classification and machine learning==
	Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="~~Jafarlou-2024~~"/>		Label propagation offers an efficient solution to the challenge of labeling datasets in machine learning by reducing the need for manual labels. Text classification utilizes a graph-based technique, where the nearest neighbor graph is built from network embeddings, and labels are extended based on cosine similarity by merging these pseudo-labeled data points into supervised learning. <ref name="Jafarlou2024"/>

76.20.252.182 at 14:05, 16 October 2024

2024-10-16T14:05:49Z

← Previous revision		Revision as of 14:05, 16 October 2024
Line 37:		Line 37:
	{{reflist}}		{{reflist}}

			<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->
	<ref name="raghavan-albert-kumara2007">Raghavan, U. N., Albert, R., & Kumara, S. (2007). "Near linear time algorithm to detect community structures in large-scale networks." arXiv preprint arXiv:0709.2938.</ref>
			*
			*
			*
			*

	<ref name="Jafarlou-2024">Jafarlou, M., & Kubek, M. M. (2024). "Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning." arXiv preprint arXiv:2410.11355.</ref>

	<ref>Zhu, X. (2002). "Learning From Labeled and Unlabeled Data With Label Propagation." Technical Report, University of Wisconsin-Madison. CiteSeerX: 10.1.1.14.3864.</ref>

			==External links==
	<ref>Newman, M. E. J. (2004). "Detecting community structure in networks." The European Physical Journal B, 38(2), 321-330. [http://www-personal.umich.edu/~mejn/papers/epjb.pdf]</ref>
			<!--- * [http://opcoast.com/demos/label_propagation/index.html An online demonstration, allowing custom inputs] - dead link --->
			* [https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/semi_supervised/_label_propagation.py Python implementation of label propagation algorithm].

			<!--- STOP! Be warned that by using this process instead of Articles for Creation, this article is subject to scrutiny. As an article in "mainspace", it will be DELETED if there are problems, not just declined. If you wish to use AfC, please return to the Wizard and continue from there. --->

	[[Category:Machine learning algorithms]]		[[Category:Machine learning algorithms]]

76.20.252.182 at 04:10, 16 October 2024

2024-10-16T04:10:45Z

← Previous revision		Revision as of 04:10, 16 October 2024
Line 35:		Line 35:

	==References==		==References==
	{{reflist:		{{reflist}}

			<ref name="raghavan-albert-kumara2007">Raghavan, U. N., Albert, R., & Kumara, S. (2007). "Near linear time algorithm to detect community structures in large-scale networks." arXiv preprint arXiv:0709.2938.</ref>

	<ref name="Jafarlou-2024">Jafarlou, M., & Kubek, M. M. (2024). "Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning." arXiv preprint arXiv:2410.11355.</ref>		<ref name="Jafarlou-2024">Jafarlou, M., & Kubek, M. M. (2024). "Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning." arXiv preprint arXiv:2410.11355.</ref>

			<ref>Zhu, X. (2002). "Learning From Labeled and Unlabeled Data With Label Propagation." Technical Report, University of Wisconsin-Madison. CiteSeerX: 10.1.1.14.3864.</ref>
	}}

	<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->
	*
	*
	*
	*



			<ref>Newman, M. E. J. (2004). "Detecting community structure in networks." The European Physical Journal B, 38(2), 321-330. [http://www-personal.umich.edu/~mejn/papers/epjb.pdf]</ref>
	==External links==
	<!--- * [http://opcoast.com/demos/label_propagation/index.html An online demonstration, allowing custom inputs] - dead link --->
	* [https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/semi_supervised/_label_propagation.py Python implementation of label propagation algorithm].

	<!--- STOP! Be warned that by using this process instead of Articles for Creation, this article is subject to scrutiny. As an article in "mainspace", it will be DELETED if there are problems, not just declined. If you wish to use AfC, please return to the Wizard and continue from there. --->

	[[Category:Machine learning algorithms]]		[[Category:Machine learning algorithms]]

76.20.252.182 at 04:06, 16 October 2024

2024-10-16T04:06:39Z

← Previous revision		Revision as of 04:06, 16 October 2024
Line 35:		Line 35:

	==References==		==References==
	{{reflist}}		{{reflist:

	<ref name="Jafarlou-2024">Jafarlou, M., & Kubek, M. M. (2024). "Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning." arXiv preprint arXiv:2410.11355.</ref>		<ref name="Jafarlou-2024">Jafarlou, M., & Kubek, M. M. (2024). "Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning." arXiv preprint arXiv:2410.11355.</ref>

			}}

	<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->		<!--- After listing your sources please cite them using inline citations and place them after the information they cite. Please see http://en.wikipedia.org/wiki/Wikipedia:REFB for instructions on how to add citations. --->