{"id":"https://openalex.org/W4389610115","doi":"https://doi.org/10.1145/3626732","title":"High-Ratio Compression for Machine-Generated Data","display_name":"High-Ratio Compression for Machine-Generated Data","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389610115","doi":"https://doi.org/10.1145/3626732"},"language":"en","primary_location":{"id":"doi:10.1145/3626732","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626732","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-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/A5107984076","display_name":"Jiujing Zhang","orcid":"https://orcid.org/0009-0007-9266-2659"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiujing Zhang","raw_affiliation_strings":["Guangzhou University & University of New South Wales, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-9266-2659","affiliations":[{"raw_affiliation_string":"Guangzhou University & University of New South Wales, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044811331","display_name":"Z. Shen","orcid":"https://orcid.org/0009-0006-4015-126X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhitao Shen","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-4015-126X","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688821","display_name":"Shiyu Yang","orcid":"https://orcid.org/0000-0002-3989-7404"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Yang","raw_affiliation_strings":["Guangzhou University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3989-7404","affiliations":[{"raw_affiliation_string":"Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018075111","display_name":"Lingkai Meng","orcid":"https://orcid.org/0009-0004-9572-6257"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingkai Meng","raw_affiliation_strings":["Ant Group & Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-9572-6257","affiliations":[{"raw_affiliation_string":"Ant Group & Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036148682","display_name":"Chuan Xiao","orcid":"https://orcid.org/0000-0001-7239-5134"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chuan Xiao","raw_affiliation_strings":["Osaka University & Nagoya University, Osaka & Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7239-5134","affiliations":[{"raw_affiliation_string":"Osaka University & Nagoya University, Osaka & Nagoya, Japan","institution_ids":["https://openalex.org/I60134161","https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014136548","display_name":"Wei Jia","orcid":"https://orcid.org/0009-0007-9823-4209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Jia","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-9823-4209","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813323","display_name":"Yue Li","orcid":"https://orcid.org/0009-0005-2913-0129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-2913-0129","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085123617","display_name":"Qinhui Sun","orcid":"https://orcid.org/0009-0006-8383-7034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinhui Sun","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-8383-7034","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385498","display_name":"Wenjie Zhang","orcid":"https://orcid.org/0000-0001-6572-2600"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenjie Zhang","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6572-2600","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079659938","display_name":"Xuemin Lin","orcid":"https://orcid.org/0000-0003-2396-7225"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemin Lin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2396-7225","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8773,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76036191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"1","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/compression-ratio","display_name":"Compression ratio","score":0.754188060760498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7389559745788574},{"id":"https://openalex.org/keywords/random-access","display_name":"Random access","score":0.6730852723121643},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6546401381492615},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4925599694252014},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4770759344100952},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4497497081756592},{"id":"https://openalex.org/keywords/data-compression-ratio","display_name":"Data compression ratio","score":0.43287867307662964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43212565779685974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25515857338905334},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.25126713514328003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16940751671791077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13289067149162292},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08513593673706055}],"concepts":[{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.754188060760498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389559745788574},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.6730852723121643},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6546401381492615},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4925599694252014},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4770759344100952},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4497497081756592},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.43287867307662964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43212565779685974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25515857338905334},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.25126713514328003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16940751671791077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13289067149162292},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08513593673706055},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626732","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626732","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2781111794","display_name":"\u81ea\u5f8b\u5354\u8abf\u578b\u30c7\u30fc\u30bf\u30d9\u30fc\u30b9\u7d71\u5408\u57fa\u76e4\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"23K17456","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3845744225","display_name":null,"funder_award_id":"2022YFB3103700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6843473724","display_name":null,"funder_award_id":"2019B1515120048","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7356995678","display_name":null,"funder_award_id":"U20B2046, U2241211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8810288059","display_name":"Intelligent Information Retrieval Systems for Text Databases of Japanese and Chinese Classics","funder_award_id":"23K25157","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1519440323","https://openalex.org/W1527356121","https://openalex.org/W1577505202","https://openalex.org/W1993819379","https://openalex.org/W1995875735","https://openalex.org/W2028785128","https://openalex.org/W2030062409","https://openalex.org/W2054046497","https://openalex.org/W2060108852","https://openalex.org/W2067436340","https://openalex.org/W2107745473","https://openalex.org/W2122962290","https://openalex.org/W2154091998","https://openalex.org/W2154900736","https://openalex.org/W2281341896","https://openalex.org/W2311411768","https://openalex.org/W2525726844","https://openalex.org/W2564774846","https://openalex.org/W2798891709","https://openalex.org/W2799221749","https://openalex.org/W2949054050","https://openalex.org/W2963737091","https://openalex.org/W2999013495","https://openalex.org/W3010666283","https://openalex.org/W3029187551","https://openalex.org/W3031206277","https://openalex.org/W3084651990","https://openalex.org/W4244796164","https://openalex.org/W4372267129"],"related_works":["https://openalex.org/W2372002319","https://openalex.org/W3047599943","https://openalex.org/W4383723869","https://openalex.org/W4384298135","https://openalex.org/W2161302774","https://openalex.org/W2388481516","https://openalex.org/W2011090518","https://openalex.org/W3080614128","https://openalex.org/W2103127675","https://openalex.org/W2945049259"],"abstract_inverted_index":{"Machine-generated":[0],"data":[1,16,62,72,101,110,115],"is":[2],"rapidly":[3],"growing":[4],"and":[5,46,61,73,147,159,166],"poses":[6],"challenges":[7],"for":[8,38],"data-intensive":[9,39],"systems,":[10],"especially":[11],"as":[12,137,139],"the":[13,18,26,67,90,140],"growth":[14,19],"of":[15,20,70],"outpaces":[17],"storage":[21,27,35],"space.":[22],"To":[23,84],"cope":[24],"with":[25],"issue,":[28],"compression":[29,44,54,78,134,146],"plays":[30],"a":[31,42,117,133,155],"critical":[32],"role":[33],"in":[34,76,99,105],"engines,":[36],"particularly":[37],"applications,":[40],"where":[41],"high":[43,138],"ratio":[45,135,165],"efficient":[47],"random":[48,122],"access":[49],"are":[50],"essential.":[51],"However,":[52],"existing":[53],"techniques":[55,142],"tend":[56],"to":[57,102,154],"focus":[58],"on":[59,116,130,162],"general-purpose":[60],"block":[63],"approaches,":[64],"but":[65],"overlook":[66],"inherent":[68],"structure":[69],"machine-generated":[71,100],"hence":[74],"result":[75],"low":[77],"ratios":[79],"or":[80],"limited":[81],"lookup":[82],"efficiency.":[83],"address":[85],"these":[86],"limitations,":[87],"we":[88],"introduce":[89],"Pattern-Based":[91],"Compression":[92],"(PBC)":[93],"algorithm,":[94],"which":[95],"specifically":[96],"targets":[97],"patterns":[98],"achieve":[103,160],"Pareto-optimality":[104],"most":[106],"cases.":[107],"Unlike":[108],"traditional":[109],"block-based":[111],"methods,":[112],"PBC":[113,153],"compresses":[114],"per-record":[118],"basis,":[119],"facilitating":[120],"rapid":[121],"access.":[123],"Our":[124],"experimental":[125],"evaluation":[126],"demonstrates":[127],"that":[128],"PBC,":[129],"average,":[131],"achieves":[132],"twice":[136],"state-of-the-art":[141],"while":[143],"maintaining":[144],"competitive":[145],"decompression":[148],"speeds.":[149],"We":[150],"also":[151],"integrate":[152],"production":[156],"database":[157],"system":[158],"improvements":[161],"both":[163],"comparison":[164],"throughput.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}