{"id":"https://openalex.org/W7140785708","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443313","title":"Dirichlet Meets Horvitz and Thompson: Estimating Homophily in Large Networks via Sampling","display_name":"Dirichlet Meets Horvitz and Thompson: Estimating Homophily in Large Networks via Sampling","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7140785708","doi":"https://doi.org/10.1109/ieeeconf67917.2025.11443313"},"language":null,"primary_location":{"id":"doi:10.1109/ieeeconf67917.2025.11443313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096912326","display_name":"Hamed Ajorlou","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hamed Ajorlou","raw_affiliation_strings":["University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006078163","display_name":"Gonzalo Mateos","orcid":"https://orcid.org/0000-0002-9847-6298"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gonzalo Mateos","raw_affiliation_strings":["University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Dept. of Electrical and Computer Engineering,Rochester,NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036583414","display_name":"Luana Ruiz","orcid":"https://orcid.org/0000-0002-9666-1211"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luana Ruiz","raw_affiliation_strings":["Johns Hopkins University,Dept. of Applied Mathematics and Statistics,Baltimore,MD"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Dept. of Applied Mathematics and Statistics,Baltimore,MD","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5096912326"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76448549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1109","last_page":"1113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.7979000210762024,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.7979000210762024,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.022700000554323196,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/homophily","display_name":"Homophily","score":0.5439000129699707},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.41440001130104065},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.3643999993801117},{"id":"https://openalex.org/keywords/distance-sampling","display_name":"Distance sampling","score":0.31360000371932983},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.29679998755455017}],"concepts":[{"id":"https://openalex.org/C2779812341","wikidata":"https://www.wikidata.org/wiki/Q5891525","display_name":"Homophily","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5299000144004822},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5085999965667725},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.41440001130104065},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3765999972820282},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C2781050692","wikidata":"https://www.wikidata.org/wiki/Q5282869","display_name":"Distance sampling","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C2985880046","wikidata":"https://www.wikidata.org/wiki/Q7410168","display_name":"Sampling theory","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf67917.2025.11443313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf67917.2025.11443313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W635323286","https://openalex.org/W1684722273","https://openalex.org/W1977661148","https://openalex.org/W2017274979","https://openalex.org/W2111754130","https://openalex.org/W2486096428","https://openalex.org/W2963316155","https://openalex.org/W2981512051","https://openalex.org/W2994097903","https://openalex.org/W3035497236","https://openalex.org/W3095521706","https://openalex.org/W3195962189","https://openalex.org/W4225149909","https://openalex.org/W4233471163","https://openalex.org/W4417053866"],"related_works":[],"abstract_inverted_index":{"Assessing":[0],"homophily":[1,67],"in":[2,11,49,124,164],"large-scale":[3],"networks":[4],"is":[5,93],"central":[6],"to":[7,26,37,65],"understanding":[8],"structural":[9],"regularities":[10],"graphs,":[12,141],"and":[13,42,120,142],"thus":[14],"inform":[15],"the":[16,38,69,79,125,132,157,160],"choice":[17],"of":[18,32,75,159],"models":[19],"(such":[20],"as":[21,122,148],"graph":[22,76,88,103],"neural":[23],"networks)":[24],"adopted":[25],"learn":[27],"from":[28,86,139,172],"network":[29,40,109,174],"data.":[30],"Evaluation":[31],"smoothness":[33],"metrics":[34],"requires":[35],"access":[36],"entire":[39],"topology":[41],"node":[43],"features,":[44],"which":[45,113],"may":[46],"be":[47,117,136],"impractical":[48],"several":[50,152],"large-scale,":[51],"dynamic,":[52],"resource-limited,":[53],"or":[54],"privacy-constrained":[55],"settings.":[56],"In":[57],"this":[58],"work,":[59],"we":[60],"propose":[61],"a":[62,94],"sampling-based":[63],"framework":[64],"estimate":[66],"via":[68],"Dirichlet":[70,91,133],"energy":[71,92,134],"(Laplacian-based":[72],"total":[73,96],"variation)":[74],"signals,":[77],"leveraging":[78],"Horvitz-Thompson":[80],"(HT)":[81],"estimator":[82],"for":[83,112],"unbiased":[84],"inference":[85],"partial":[87],"observations.":[89],"The":[90],"so-termed":[95],"(of":[97],"squared":[98],"nodal":[99],"feature":[100],"deviations)":[101],"over":[102],"edges;":[104],"hence,":[105],"estimable":[106],"under":[107],"general":[108],"sampling":[110],"designs":[111],"edge-inclusion":[114],"probabilities":[115],"can":[116,135],"analytically":[118],"derived":[119],"used":[121],"weights":[123],"proposed":[126,161],"HT":[127,162],"estimator.":[128],"We":[129],"establish":[130],"that":[131],"consistently":[137],"estimated":[138],"sampled":[140,173],"empirically":[143],"study":[144],"other":[145],"heterophily":[146],"measures":[147],"well.":[149],"Experiments":[150],"on":[151],"heterophilic":[153],"benchmark":[154],"datasets":[155],"demonstrate":[156],"effectiveness":[158],"estimators":[163],"reliably":[165],"capturing":[166],"homophilic":[167],"structure":[168],"(or":[169],"lack":[170],"thereof)":[171],"measurements.":[175]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2026-03-27T00:00:00"}