{"id":1005,"date":"2017-11-30T12:23:08","date_gmt":"2017-11-30T11:23:08","guid":{"rendered":"http:\/\/mathfinance.sns.it\/?p=1005"},"modified":"2017-11-30T12:29:48","modified_gmt":"2017-11-30T11:29:48","slug":"p-barucca-p-mazzarisi-f-lillo-d-tantari-2017-disentangling-group-and-link-persistence-in-dynamic-stochastic-block-models","status":"publish","type":"post","link":"http:\/\/mathfinance.sns.it\/index.php\/p-barucca-p-mazzarisi-f-lillo-d-tantari-2017-disentangling-group-and-link-persistence-in-dynamic-stochastic-block-models\/","title":{"rendered":"P.Barucca, P.Mazzarisi, F.Lillo, D.Tantari (2017), <em> Disentangling group and link persistence in dynamic stochastic block models<\/em>"},"content":{"rendered":"<p>We study the inference of a model of dynamic networks in which both communities and<br \/>\nlinks keep memory of previous network states. By considering maximum likelihood inference from<br \/>\nsingle snapshot observations of the network, we show that link persistence makes the inference of<br \/>\ncommunities harder, decreasing the detectability threshold, while community persistence tends to make<br \/>\nit easier. We analytically show that communities inferred from single network snapshot can share a<br \/>\nmaximum overlap with the underlying communities of a specific previous instant in time. This leads<br \/>\nto time-lagged inference: the identification of past communities rather than present ones. Finally<br \/>\nwe compute the time lag and propose a corrected algorithm, the Lagged Snapshot Dynamic (LSD)<br \/>\nalgorithm, for community detection in dynamic networks. We analytically and numerically characterize<br \/>\nthe detectability transitions of such algorithm as a function of the memory parameters of the model.<\/p>\n<p><a href=\"https:\/\/arxiv.org\/pdf\/1701.05804.pdf\">https:\/\/arxiv.org\/pdf\/1701.05804.pdf<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We study the inference of a model of dynamic networks in which both communities and links keep memory of previous network states. By considering maximum likelihood inference from single snapshot observations of the network, we show that link persistence makes the inference of communities harder, decreasing the detectability threshold, while community persistence tends to make [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[11],"tags":[],"_links":{"self":[{"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/posts\/1005"}],"collection":[{"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/comments?post=1005"}],"version-history":[{"count":5,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/posts\/1005\/revisions"}],"predecessor-version":[{"id":1011,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/posts\/1005\/revisions\/1011"}],"wp:attachment":[{"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/media?parent=1005"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/categories?post=1005"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/mathfinance.sns.it\/index.php\/wp-json\/wp\/v2\/tags?post=1005"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}