{"id":"https://openalex.org/W2782586228","doi":"https://doi.org/10.1109/bigdata.2017.8258022","title":"Application-specific graph sampling for frequent subgraph mining and community detection","display_name":"Application-specific graph sampling for frequent subgraph mining and community detection","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2782586228","doi":"https://doi.org/10.1109/bigdata.2017.8258022","mag":"2782586228"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025824247","display_name":"Sumit Purohit","orcid":"https://orcid.org/0000-0002-6483-486X"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit Purohit","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016440514","display_name":"Sutanay Choudhury","orcid":"https://orcid.org/0000-0001-7352-2035"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sutanay Choudhury","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044712355","display_name":"Lawrence B. Holder","orcid":"https://orcid.org/0000-0002-6586-3144"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence B. Holder","raw_affiliation_strings":["Washington State University, Pullman, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, WA, USA","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1000","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224571704864502},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.6869277358055115},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.602146565914154},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5795646905899048},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46540266275405884},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43308889865875244},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4200207591056824},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39255490899086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16158348321914673},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1312292218208313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224571704864502},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.6869277358055115},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.602146565914154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5795646905899048},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46540266275405884},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43308889865875244},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4200207591056824},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39255490899086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16158348321914673},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1312292218208313},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2017.8258022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W16743356","https://openalex.org/W1932742904","https://openalex.org/W2045025184","https://openalex.org/W2048596679","https://openalex.org/W2055935910","https://openalex.org/W2111708605","https://openalex.org/W2122255072","https://openalex.org/W2124450885","https://openalex.org/W2131681506","https://openalex.org/W2143211346","https://openalex.org/W2146008005","https://openalex.org/W2171935404","https://openalex.org/W2494166009","https://openalex.org/W2755088640","https://openalex.org/W2963161123","https://openalex.org/W3099768174"],"related_works":["https://openalex.org/W2154222238","https://openalex.org/W2106626222","https://openalex.org/W2980866815","https://openalex.org/W1562405179","https://openalex.org/W2125493559","https://openalex.org/W1544909909","https://openalex.org/W2002053721","https://openalex.org/W2001641889","https://openalex.org/W2310552679","https://openalex.org/W4308987612"],"abstract_inverted_index":{"Graph":[0],"mining":[1,87,138],"is":[2,43,74,172],"an":[3,173],"important":[4],"data":[5,60],"analysis":[6,53],"methodology,":[7],"but":[8],"struggles":[9],"as":[10,90,104,179],"the":[11,31,46,51,59,63,149,162,180,186,192],"input":[12,32,154],"graph":[13,33,70,86,101,112,137,155],"size":[14,182],"increases.":[15],"The":[16,38],"scalability":[17],"and":[18,34,71,95,107,113,120,205],"usability":[19],"challenges":[20],"posed":[21],"by":[22],"such":[23,89,103],"large":[24],"graphs":[25,118],"make":[26],"it":[27],"imperative":[28],"to":[29,44,49,109,144,160,189],"sample":[30,110,181],"reduce":[35],"its":[36],"size.":[37],"critical":[39],"challenge":[40],"in":[41],"sampling":[42,72,83,133,164,203],"identify":[45],"appropriate":[47],"algorithm":[48,73],"insure":[50],"resulting":[52],"does":[54],"not":[55],"suffer":[56],"heavily":[57],"from":[58],"reduction.":[61],"Predicting":[62],"expected":[64],"performance":[65,170,193],"degradation":[66,171,194],"for":[67,85,116,135],"a":[68,111,196],"given":[69],"also":[75,129,167],"useful.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"present":[81,130,141,185],"different":[82],"approaches":[84],"applications":[88],"Frequent":[91],"Subgrpah":[92],"Mining":[93],"(FSM),":[94],"Community":[96],"Detection":[97],"(CD).":[98],"We":[99,128,140,166,184],"explore":[100],"metrics":[102],"PageRank,":[105],"Triangles,":[106],"Diversity":[108,121],"conclude":[114,168],"that":[115,146,169,191],"heterogeneous":[117],"Triangles":[119],"perform":[122],"better":[123],"than":[124,176],"degree":[125],"based":[126],"metrics.":[127],"two":[131],"new":[132],"variations":[134],"targeted":[136],"applications.":[139],"empirical":[142,187],"results":[143,188,206],"show":[145,190],"knowledge":[147],"of":[148,202],"target":[150],"application,":[151],"along":[152],"with":[153],"properties":[156],"can":[157],"be":[158],"used":[159],"select":[161],"best":[163],"algorithm.":[165],"abrupt,":[174],"rather":[175],"gradual":[177],"phenomena,":[178],"decreases.":[183],"follows":[195],"logistic":[197],"function.":[198],"Original":[199],"Datasets,":[200],"implementation":[201],"algorithms,":[204],"are":[207],"available":[208],"online.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}