Sequential Edge Clustering in Temporal Multigraphs

Sequential Edge Clustering in Temporal Multigraphs

Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ghalebi, Elahe, Mahyar, Hamidreza, Grosu, Radu, Taylor, Graham W, Williamson, Sinead A
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Learning
Statistics - Machine Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ghalebi, Elahe
Mahyar, Hamidreza
Grosu, Radu
Taylor, Graham W
Williamson, Sinead A
description Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.
doi_str_mv 10.48550/arxiv.1905.11724
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1905_11724</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1905_11724</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-6e7287260db39c060b994db2080532732532c0067d4f264c4801468e3fbcda753</originalsourceid><addsrcrecordid>eNotzruOgkAYBeBptjCuD2AlLwD-cx9KQ_CSuLGQngzMgJMAyw5g9O29bXNOcZKTD6ElhogpzmGt_c1dIxwDjzCWhM0QOdu_yXaj002QmtoGSTMNo_WuqwPXBZlt-1__3H6mZnS11_1l-EZflW4Gu_jvOcq2aZbsw-Npd0g2x1ALyUJhJVGSCDAFjUsQUMQxMwUBBZwSSckzSwAhDauIYCVTgJlQllZFabTkdI5Wn9s3Ou-9a7W_5y98_sbTB3BbPVw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Sequential Edge Clustering in Temporal Multigraphs</title><source>arXiv.org</source><creator>Ghalebi, Elahe ; Mahyar, Hamidreza ; Grosu, Radu ; Taylor, Graham W ; Williamson, Sinead A</creator><creatorcontrib>Ghalebi, Elahe ; Mahyar, Hamidreza ; Grosu, Radu ; Taylor, Graham W ; Williamson, Sinead A</creatorcontrib><description>Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.</description><identifier>DOI: 10.48550/arxiv.1905.11724</identifier><language>eng</language><subject>Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2019-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1905.11724$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1905.11724$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ghalebi, Elahe</creatorcontrib><creatorcontrib>Mahyar, Hamidreza</creatorcontrib><creatorcontrib>Grosu, Radu</creatorcontrib><creatorcontrib>Taylor, Graham W</creatorcontrib><creatorcontrib>Williamson, Sinead A</creatorcontrib><title>Sequential Edge Clustering in Temporal Multigraphs</title><description>Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.</description><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzruOgkAYBeBptjCuD2AlLwD-cx9KQ_CSuLGQngzMgJMAyw5g9O29bXNOcZKTD6ElhogpzmGt_c1dIxwDjzCWhM0QOdu_yXaj002QmtoGSTMNo_WuqwPXBZlt-1__3H6mZnS11_1l-EZflW4Gu_jvOcq2aZbsw-Npd0g2x1ALyUJhJVGSCDAFjUsQUMQxMwUBBZwSSckzSwAhDauIYCVTgJlQllZFabTkdI5Wn9s3Ou-9a7W_5y98_sbTB3BbPVw</recordid><startdate>20190528</startdate><enddate>20190528</enddate><creator>Ghalebi, Elahe</creator><creator>Mahyar, Hamidreza</creator><creator>Grosu, Radu</creator><creator>Taylor, Graham W</creator><creator>Williamson, Sinead A</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190528</creationdate><title>Sequential Edge Clustering in Temporal Multigraphs</title><author>Ghalebi, Elahe ; Mahyar, Hamidreza ; Grosu, Radu ; Taylor, Graham W ; Williamson, Sinead A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-6e7287260db39c060b994db2080532732532c0067d4f264c4801468e3fbcda753</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Ghalebi, Elahe</creatorcontrib><creatorcontrib>Mahyar, Hamidreza</creatorcontrib><creatorcontrib>Grosu, Radu</creatorcontrib><creatorcontrib>Taylor, Graham W</creatorcontrib><creatorcontrib>Williamson, Sinead A</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ghalebi, Elahe</au><au>Mahyar, Hamidreza</au><au>Grosu, Radu</au><au>Taylor, Graham W</au><au>Williamson, Sinead A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sequential Edge Clustering in Temporal Multigraphs</atitle><date>2019-05-28</date><risdate>2019</risdate><abstract>Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ignore temporal dynamics in the network. We propose a dynamic nonparametric model for interaction graphs that combine the sparsity of the exchangeable models with dynamic clustering patterns that tend to reinforce recent behavioral patterns. We show that our method yields improved held-out likelihood over stationary variants, and impressive predictive performance against a range of state-of-the-art dynamic interaction graph models.</abstract><doi>10.48550/arxiv.1905.11724</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1905.11724
ispartof
issn
language eng
recordid cdi_arxiv_primary_1905_11724
source arXiv.org
subjects Computer Science - Learning
Statistics - Machine Learning
title Sequential Edge Clustering in Temporal Multigraphs
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T15%3A11%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sequential%20Edge%20Clustering%20in%20Temporal%20Multigraphs&rft.au=Ghalebi,%20Elahe&rft.date=2019-05-28&rft_id=info:doi/10.48550/arxiv.1905.11724&rft_dat=%3Carxiv_GOX%3E1905_11724%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true