{"id":"https://openalex.org/W4416023999","doi":"https://doi.org/10.1109/infocom59046.2026.11571516","title":"EntroGD: Scalable Generalized Deduplication for Efficient Direct Analytics on Compressed IoT Data","display_name":"EntroGD: Scalable Generalized Deduplication for Efficient Direct Analytics on Compressed IoT Data","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W4416023999","doi":"https://doi.org/10.1109/infocom59046.2026.11571516"},"language":"en","primary_location":{"id":"doi:10.1109/infocom59046.2026.11571516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.04148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006177109","display_name":"Xiaobo Zhao","orcid":"https://orcid.org/0000-0003-0531-8037"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhao","raw_affiliation_strings":["Aarhus University,DIGIT,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aarhus University,DIGIT,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110828662","display_name":"Daniel E. Lucani","orcid":"https://orcid.org/0000-0001-5325-8863"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel E. Lucani","raw_affiliation_strings":["Aarhus University,DIGIT,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aarhus University,DIGIT,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00374616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.17069999873638153,"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"}},"topics":[{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.17069999873638153,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.10350000113248825,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.093299999833107,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/scalability","display_name":"Scalability","score":0.7415000200271606},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6771000027656555},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.6355000138282776},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.515999972820282},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.5109999775886536},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49540001153945923},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.40700000524520874},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.4065999984741211},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091999888420105},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7415000200271606},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6355000138282776},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/infocom59046.2026.11571516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.04148","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.04148","pdf_url":"https://arxiv.org/pdf/2511.04148","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:doi:10.48550/arxiv.2511.04148","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:publications/c69896c5-6f82-429b-a6b1-2e34d4ed978b","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/c69896c5-6f82-429b-a6b1-2e34d4ed978b","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhao, X & Lucani R\u00f6tter, D E 2026, EntroGD: Scalable Generalized Deduplication for Efficient Direct Analytics on Compressed IoT Data. in IEEE INFOCOM Workshops. IEEE.","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2511.04148","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.04148","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.04148","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.04148","pdf_url":"https://arxiv.org/pdf/2511.04148","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416023999.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Massive":[0],"data":[1,130],"streams":[2],"from":[3,65],"IoT":[4,101,157],"and":[5,15,32,89,149],"cyber-physical":[6],"systems":[7],"must":[8],"be":[9],"processed":[10],"under":[11],"strict":[12],"bandwidth,":[13],"latency,":[14],"resource":[16],"constraints.":[17],"Generalized":[18],"Deduplication":[19],"(GD)":[20],"is":[21],"a":[22,75,147],"promising":[23],"lossless":[24],"compression":[25,66],"framework,":[26],"as":[27],"it":[28],"supports":[29],"random":[30],"access":[31,123],"direct":[33,153],"analytics":[34,121,154],"on":[35,99,155],"compressed":[36,156],"data.":[37,158],"However,":[38],"existing":[39],"GD":[40,59,116],"algorithms":[41],"exhibit":[42],"quadratic":[43],"complexity":[44,71],"$\\mathcal{O}(nd^{2})$,":[45],"which":[46],"limits":[47],"their":[48],"scalability":[49],"for":[50,87,152],"high-dimensional":[51],"datasets.":[52],"This":[53],"paper":[54],"proposes":[55],"\\textbf{EntroGD},":[56],"an":[57],"entropy-guided":[58],"framework":[60],"that":[61,104],"decouples":[62],"analytical":[63],"fidelity":[64],"efficiency":[67],"to":[68,83,95,111,114,124,137],"achieve":[69],"linear":[70],"$\\mathcal{O}(nd)$.":[72],"EntroGD":[73,105,132,145],"adopts":[74],"two-stage":[76],"design,":[77],"first":[78],"constructing":[79],"compact":[80],"condensed":[81],"samples":[82],"preserve":[84],"information":[85],"critical":[86],"analytics,":[88],"then":[90],"applying":[91],"entropy-based":[92],"bit":[93],"selection":[94],"maximize":[96],"compression.":[97],"Experiments":[98],"18":[100],"datasets":[102],"show":[103],"reduces":[106],"configuration":[107],"time":[108],"by":[109,119,135],"up":[110,136],"$53.5\\times$":[112],"compared":[113],"state-of-the-art":[115],"compressors.":[117],"Moreover,":[118],"enabling":[120],"with":[122,139],"only":[125],"$2.6\\%$":[126],"of":[127],"the":[128],"original":[129],"volume,":[131],"accelerates":[133],"clustering":[134],"$31.6\\times$":[138],"negligible":[140],"loss":[141],"in":[142],"accuracy.":[143],"Overall,":[144],"provides":[146],"scalable":[148],"system-efficient":[150],"solution":[151]},"counts_by_year":[],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-11-08T00:00:00"}