<?xml-model href='http://www.tei-c.org/release/xml/tei/custom/schema/relaxng/tei_all.rng' schematypens='http://relaxng.org/ns/structure/1.0'?><TEI xmlns="http://www.tei-c.org/ns/1.0">
	<teiHeader>
		<fileDesc>
			<titleStmt><title level='a'>Efficient Algorithms for Attributed Graph Alignment with Vanishing Edge Correlation</title></titleStmt>
			<publicationStmt>
				<publisher>Proceedings of Machine Learning Research,  37th Annual Conference on Learning Theory</publisher>
				<date>06/30/2024</date>
			</publicationStmt>
			<sourceDesc>
				<bibl> 
					<idno type="par_id">10580424</idno>
					<idno type="doi"></idno>
					
					<author>Ziao Wang</author><author>Weina Wang</author><author>Lele Wang</author>
				</bibl>
			</sourceDesc>
		</fileDesc>
		<profileDesc>
			<abstract><ab><![CDATA[The graph alignment problem, also referred to as the graph matching or noisy graph isomorphism problem, is the problem of finding the correspondence between the vertices of two correlated graphs. This problem has garnered significant attention due to its widespread use in various realworld applications (Singh et al., 2007;Cho and Lee, 2012). Extensive study has been done on polynomial-time algorithms for the graph alignment problem under the Erdős-Rényi graph pair model G(n, q, ⇢), where the two graphs are Erdős-Rényi graphs with n vertices and edge probability q, correlated under certain vertex correspondence. The correlation coefficient between the corresponding edges in the two graphs is given by ⇢. Given a pair of graphs generated from the model, the goal is to exactly recover the vertex correspondence between the two graphs. Polynomial-time algorithms for graph alignment have been studied in the line of work (]]></ab></abstract>
		</profileDesc>
	</teiHeader>
	<text><body><div/></body></text>
</TEI>
