{"id":"https://openalex.org/W6960166088","doi":"https://doi.org/10.13016/ojrw-lj3b","title":"The Shuffling Effect: Vertex Label Error\u2019s Impact on Hypothesis Testing, Classification, and Clustering in Graph Data","display_name":"The Shuffling Effect: Vertex Label Error\u2019s Impact on Hypothesis Testing, Classification, and Clustering in Graph Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6960166088","doi":"https://doi.org/10.13016/ojrw-lj3b"},"language":"en","primary_location":{"id":"pmh:oai:drum.lib.umd.edu:1903/32836","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/32836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/ojrw-lj3b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Saxena, Ayushi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saxena, Ayushi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10012","display_name":"Genetic diversity and population structure","score":0.4636000096797943,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10012","display_name":"Genetic diversity and population structure","score":0.4636000096797943,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.03830000013113022,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.03759999945759773,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.8339999914169312},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6212999820709229},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.619700014591217},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.585099995136261},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.46129998564720154},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4034000039100647},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3817000091075897},{"id":"https://openalex.org/keywords/complex-network","display_name":"Complex network","score":0.37369999289512634},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.3675999939441681}],"concepts":[{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.8339999914169312},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.585099995136261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5555999875068665},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5038999915122986},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C34947359","wikidata":"https://www.wikidata.org/wiki/Q665189","display_name":"Complex network","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C2779982251","wikidata":"https://www.wikidata.org/wiki/Q25053762","display_name":"Stochastic block model","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C89694873","wikidata":"https://www.wikidata.org/wiki/Q4810299","display_name":"Assortativity","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C137753397","wikidata":"https://www.wikidata.org/wiki/Q2434424","display_name":"Network science","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2816999852657318},{"id":"https://openalex.org/C2780600066","wikidata":"https://www.wikidata.org/wiki/Q7239828","display_name":"Preferential attachment","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:drum.lib.umd.edu:1903/32836","is_oa":false,"landing_page_url":"http://hdl.handle.net/1903/32836","pdf_url":null,"source":{"id":"https://openalex.org/S4306401518","display_name":"University Libraries (University of Maryland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"doi:10.13016/ojrw-lj3b","is_oa":true,"landing_page_url":"https://doi.org/10.13016/ojrw-lj3b","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.13016/ojrw-lj3b","is_oa":true,"landing_page_url":"https://doi.org/10.13016/ojrw-lj3b","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Collection"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"prevalence":[2],"of":[3,25,37,49,83,89,96,135,172,179,194,208,228,249],"graph":[4,138,186,209],"and":[5,15,41,75,123,140,150,164,197,226,237],"network-valued":[6],"data":[7],"across":[8,61,232],"various":[9],"disciplines":[10],"has":[11],"prompted":[12],"significant":[13],"interest":[14],"research":[16,242],"in":[17,69,105,148,176,243,253],"recent":[18],"years.":[19],"This":[20,63],"dissertation":[21],"explores":[22],"the":[23,32,47,81,103,119,133,177,192,199,206,224,247],"impact":[24],"vertex":[26,29,59,84,110,180,195,230],"shuffling,":[27],"or":[28],"misalignment,":[30],"on":[31,86,102,118,137,156],"statistical":[33,106,250],"network":[34,51,98,127,234,255],"inference":[35,235,251],"tasks":[36,236],"hypothesis":[38,99],"testing,":[39,100],"classification,":[40],"clustering.":[42],"Our":[43,202],"focus":[44],"is":[45],"within":[46],"framework":[48],"multiple":[50,233],"inference,":[52],"where":[53],"existing":[54],"methodologies":[55,166,252],"often":[56],"assume":[57],"known":[58],"correspondence":[60],"networks.":[62],"assumption":[64],"frequently":[65],"does":[66],"not":[67],"hold":[68],"practice.":[70],"Through":[71],"theoretical":[72],"analyses,":[73],"simulations,":[74],"experiments,":[76],"we":[77],"aim":[78],"to":[79,245],"reveal":[80],"effects":[82,134,193],"shuffling":[85,136,231],"different":[87],"types":[88],"performance.Our":[90],"investigation":[91],"begins":[92],"with":[93],"an":[94],"examination":[95],"two-sample":[97],"focusing":[101],"decrease":[104],"power":[107],"resulting":[108],"from":[109],"shuffling.":[111,181],"In":[112],"this":[113],"work,":[114],"our":[115],"analysis":[116],"focuses":[117],"random":[120],"dot":[121],"product":[122],"stochastic":[124],"block":[125],"model":[126],"settings.":[128],"Subsequent":[129],"chapters":[130],"delve":[131],"into":[132],"classification":[139],"clustering,":[141],"showcasing":[142],"how":[143,185],"misalignment":[144,196],"negatively":[145],"impacts":[146],"accuracy":[147],"categorizing":[149],"clustering":[151,165],"graphs":[152],"(and":[153],"vertices)":[154],"based":[155],"their":[157],"structural":[158],"characteristics.":[159],"Various":[160],"machine":[161],"learning":[162],"algorithms":[163,188],"are":[167],"explored,":[168],"revealing":[169],"a":[170,212],"theme":[171],"consistent":[173],"performance":[174],"degradation":[175],"presence":[178],"We":[182],"also":[183,204],"explore":[184],"matching":[187,210],"can":[189,217],"potentially":[190],"mitigate":[191],"recover":[198],"lost":[200],"performance.":[201],"findings":[203,222],"highlight":[205,223],"risk":[207],"as":[211,215],"pre-processing":[213],"tool,":[214],"it":[216],"induce":[218],"artificial":[219],"signal.":[220],"These":[221],"difficulties":[225],"subtleties":[227],"addressing":[229],"suggest":[238],"avenues":[239],"for":[240],"future":[241],"order":[244],"enhance":[246],"robustness":[248],"complex":[254],"environments.":[256]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}