{"id":"https://openalex.org/W7151410332","doi":"https://doi.org/10.1145/3786660","title":"Improving LZ4 for Effective Compression and Efficient Query","display_name":"Improving LZ4 for Effective Compression and Efficient Query","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7151410332","doi":"https://doi.org/10.1145/3786660"},"language":"en","primary_location":{"id":"doi:10.1145/3786660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786660","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3786660","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133093342","display_name":"Zhiheng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-6727-9143","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121211861","display_name":"Shaoxu Song","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9503-2755","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38866055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.36629998683929443,"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":0.36629998683929443,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.32429999113082886,"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/T11106","display_name":"Data Management and Algorithms","score":0.24199999868869781,"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/hash-function","display_name":"Hash function","score":0.6327000260353088},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.6274999976158142},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6018000245094299},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5823000073432922},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.576200008392334},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4803999960422516},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4796000123023987},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.47679999470710754},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.4586000144481659},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.4440000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007000088691711},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6327000260353088},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6018000245094299},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5641000270843506},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4803999960422516},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.47679999470710754},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.4586000144481659},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3752000033855438},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.3569999933242798},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.3474999964237213},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C121610932","wikidata":"https://www.wikidata.org/wiki/Q243754","display_name":"Binary search algorithm","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C136736807","wikidata":"https://www.wikidata.org/wiki/Q818943","display_name":"Range query (database)","level":5,"score":0.2667999863624573},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786660","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3786660","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786660","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1971849009","https://openalex.org/W2005112390","https://openalex.org/W2107745473","https://openalex.org/W2122962290","https://openalex.org/W2170862288","https://openalex.org/W2294581520","https://openalex.org/W2303422468","https://openalex.org/W2613624106","https://openalex.org/W2943460388","https://openalex.org/W2962771342","https://openalex.org/W3005703985","https://openalex.org/W3006971682","https://openalex.org/W4381326806","https://openalex.org/W4389539860","https://openalex.org/W4393180321","https://openalex.org/W4404181332","https://openalex.org/W6907814131","https://openalex.org/W6926303013","https://openalex.org/W6926431361","https://openalex.org/W6926664573","https://openalex.org/W6945003744"],"related_works":[],"abstract_inverted_index":{"LZ4":[0,38,107],"is":[1],"a":[2,66,71,139],"compression":[3,39,50,67,82,166],"algorithm":[4,40,68],"widely":[5],"adopted":[6],"in":[7,106,150],"many":[8],"database":[9],"systems,":[10],"which":[11,47],"surprisingly":[12],"has":[13,41],"no":[14],"support":[15],"for":[16,28,138],"directly":[17],"querying":[18],"the":[19,37,53,81,86,112,118,135,146],"compressed":[20,93,104,123],"data.":[21],"Existing":[22],"systems":[23],"rely":[24],"on":[25],"full":[26],"decompression":[27],"query":[29,34,57,88,103,148,169],"processing,":[30],"leading":[31],"to":[32,75,101,133],"increased":[33],"latency.":[35],"Moreover,":[36],"issues":[42],"like":[43],"long":[44],"match":[45],"dependency,":[46],"reduces":[48],"both":[49],"effectiveness":[51,167],"and":[52,84,168],"efficiency":[54],"of":[55,117],"compressed-data":[56,87,147],"processing.":[58],"In":[59],"this":[60],"paper,":[61],"(1)":[62],"we":[63,121,144],"propose":[64,92],"LZV,":[65],"that":[69,97,127,161],"employs":[70],"variable-length":[72],"hash":[73],"mechanism":[74],"identify":[76],"maximal":[77],"matches,":[78],"significantly":[79,164],"improving":[80],"ratio":[83],"reducing":[85],"overhead.":[89],"(2)":[90],"We":[91],"index":[94,137],"search":[95,125,132],"method":[96,126],"leverages":[98],"auxiliary":[99],"structure":[100],"efficiently":[102],"data":[105],"format":[108],"directly.":[109],"(3)":[110],"Leveraging":[111],"ordered,":[113],"quasi-uniformly":[114],"spaced":[115],"nature":[116],"key":[119,124,141],"column,":[120],"introduce":[122],"integrates":[128],"prediction":[129],"with":[130],"binary":[131],"retrieve":[134],"corresponding":[136],"given":[140],"efficiently.":[142],"Finally,":[143],"implement":[145],"pipeline":[149],"Apache":[151],"TsFile,":[152],"an":[153],"open-source":[154],"KV":[155],"storage":[156],"system.":[157],"Experimental":[158],"results":[159],"show":[160],"our":[162],"approach":[163],"improves":[165],"efficiency.":[170]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-04-08T00:00:00"}