{"id":"https://openalex.org/W4406458089","doi":"https://doi.org/10.1109/bigdata62323.2024.10825287","title":"Shrink: Data Compression by Semantic Extraction and Residuals Encoding","display_name":"Shrink: Data Compression by Semantic Extraction and Residuals Encoding","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458089","doi":"https://doi.org/10.1109/bigdata62323.2024.10825287"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchprofiles.ku.dk/da/publications/52822c23-f7b9-428c-9520-3e5b3e6c604d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101715065","display_name":"G. Sun","orcid":"https://orcid.org/0000-0003-3162-3350"},"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":true,"raw_author_name":"Guoyou Sun","raw_affiliation_strings":["Aarhus University,DIGIT and Department of Electrical and Computer Engineering,Denmark"],"affiliations":[{"raw_affiliation_string":"Aarhus University,DIGIT and Department of Electrical and Computer Engineering,Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061315439","display_name":"Panagiotis Karras","orcid":"https://orcid.org/0000-0002-7642-0875"},"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":"Panagiotis Karras","raw_affiliation_strings":["Aarhus University,DIGIT and Department of Computer Science,Denmark"],"affiliations":[{"raw_affiliation_string":"Aarhus University,DIGIT and Department of Computer Science,Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082693278","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0001-7041-6704"},"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":"Qi Zhang","raw_affiliation_strings":["Aarhus University,DIGIT and Department of Electrical and Computer Engineering,Denmark"],"affiliations":[{"raw_affiliation_string":"Aarhus University,DIGIT and Department of Electrical and Computer Engineering,Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101715065"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":0.3535,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70540525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7137200832366943},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.617770254611969},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6069608330726624},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5533989667892456},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5173068046569824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667505383491516},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3593764305114746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3518263101577759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137200832366943},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.617770254611969},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6069608330726624},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5533989667892456},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5173068046569824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667505383491516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3593764305114746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3518263101577759},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/52822c23-f7b9-428c-9520-3e5b3e6c604d","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/52822c23-f7b9-428c-9520-3e5b3e6c604d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun , G , Karras , P & Zhang , Q 2024 , Shrink : Data Compression by Semantic Extraction and Residuals Encoding . in W Ding , C-T Lu , F Wang , L Di , K Wu , J Huan , R Nambiar , J Li , F Ilievski , R Baeza-Yates & X Hu (eds) , Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024 . IEEE , pp. 650-659 , 2024 IEEE International Conference on Big Data, BigData 2024 , Washington , United States , 15/12/2024 . https://doi.org/10.1109/BigData62323.2024.10825287","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/52822c23-f7b9-428c-9520-3e5b3e6c604d","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/52822c23-f7b9-428c-9520-3e5b3e6c604d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sun , G , Karras , P & Zhang , Q 2024 , Shrink : Data Compression by Semantic Extraction and Residuals Encoding . in W Ding , C-T Lu , F Wang , L Di , K Wu , J Huan , R Nambiar , J Li , F Ilievski , R Baeza-Yates & X Hu (eds) , Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024 . IEEE , pp. 650-659 , 2024 IEEE International Conference on Big Data, BigData 2024 , Washington , United States , 15/12/2024 . https://doi.org/10.1109/BigData62323.2024.10825287","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3791286706","display_name":null,"funder_award_id":"168043","funder_id":"https://openalex.org/F4320322885","funder_display_name":"NordForsk"},{"id":"https://openalex.org/G7767403542","display_name":null,"funder_award_id":"2079-00040B","funder_id":"https://openalex.org/F4320313796","funder_display_name":"Innovationsfonden"}],"funders":[{"id":"https://openalex.org/F4320309928","display_name":"Aarhus Universitet","ror":"https://ror.org/01aj84f44"},{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"},{"id":"https://openalex.org/F4320322885","display_name":"NordForsk","ror":"https://ror.org/05bqzfg94"},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1510763264","https://openalex.org/W1519039476","https://openalex.org/W1987752353","https://openalex.org/W2049520215","https://openalex.org/W2097098223","https://openalex.org/W2109289209","https://openalex.org/W2135134185","https://openalex.org/W2142285455","https://openalex.org/W2161488606","https://openalex.org/W2163336863","https://openalex.org/W2294581520","https://openalex.org/W2886377182","https://openalex.org/W2948233700","https://openalex.org/W3034136960","https://openalex.org/W3047599943","https://openalex.org/W3098592065","https://openalex.org/W4226425434","https://openalex.org/W4312429406","https://openalex.org/W4313010588","https://openalex.org/W4380433174","https://openalex.org/W4381621963","https://openalex.org/W4386123432","https://openalex.org/W4386196482","https://openalex.org/W4391305309","https://openalex.org/W6676015427","https://openalex.org/W6683504902","https://openalex.org/W6792985385"],"related_works":["https://openalex.org/W4235381733","https://openalex.org/W2355022049","https://openalex.org/W2060429446","https://openalex.org/W2741782512","https://openalex.org/W3011302839","https://openalex.org/W2392958391","https://openalex.org/W3155227409","https://openalex.org/W2898682874","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0],"distributed":[1],"data":[2,39,51,68,91,98,125],"infrastructure":[3],"in":[4,70,142],"Internet":[5],"of":[6,29,73],"Things":[7],"(IoT)":[8],"ecosystems":[9],"requires":[10],"efficient":[11],"data-series":[12],"compression":[13,27,31,52,58,105,121,143],"methods,":[14,135],"as":[15,17,100,109,111],"well":[16,110],"the":[18,26,71,96,147],"capability":[19],"to":[20,76,90,102,139],"meet":[21],"different":[22],"accuracy":[23],"demands.":[24],"However,":[25],"performance":[28],"existing":[30],"methods":[32],"degrades":[33],"sharply":[34],"when":[35],"calling":[36],"for":[37],"ultra-accurate":[38],"recovery.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"introduce":[45],"Shrink,":[46],"a":[47,56,78,83,137],"novel":[48],"highly":[49],"accurate":[50],"method":[53],"that":[54,131],"offers":[55],"higher":[57],"ratio":[59,122,144],"and":[60],"lower":[61],"runtime":[62],"than":[63],"prior":[64],"compressors.":[65],"Shrink":[66,115,132],"extracts":[67],"semantics":[69],"form":[72],"linear":[74],"segments":[75],"construct":[77],"compact":[79],"knowledge":[80],"base,":[81],"using":[82],"dynamic":[84],"error":[85],"threshold":[86],"which":[87],"can":[88],"adapt":[89],"characteristics.":[92],"Then,":[93],"it":[94],"captures":[95],"remaining":[97],"details":[99],"residuals":[101],"support":[103],"lossy":[104],"at":[106],"diverse":[107],"resolutions":[108],"lossless":[112],"compression.":[113],"As":[114],"effectively":[116],"identifies":[117],"repeated":[118],"semantics,":[119],"its":[120],"increases":[123],"with":[124],"size.":[126],"Our":[127],"experimental":[128],"evaluation":[129],"demonstrates":[130],"outperforms":[133],"state-of-art":[134],"achieving":[136],"twofold":[138],"fivefold":[140],"improvement":[141],"depending":[145],"on":[146],"dataset.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}