{"id":"https://openalex.org/W4409657484","doi":"https://doi.org/10.1145/3696410.3714655","title":"MSDZip: Universal Lossless Compression for Multi-source Data via Stepwise-parallel and Learning-based Prediction","display_name":"MSDZip: Universal Lossless Compression for Multi-source Data via Stepwise-parallel and Learning-based Prediction","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409657484","doi":"https://doi.org/10.1145/3696410.3714655"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714655","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714655","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101194582","display_name":"Huidong Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huidong Ma","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104667219","display_name":"Hui Sun","orcid":"https://orcid.org/0000-0003-0290-142X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Hui Sun","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China and Nanyang Technological University, Nanyang, Singapore"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China and Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I205237279","https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010021903","display_name":"Liping Yi","orcid":"https://orcid.org/0000-0001-6236-3673"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Liping Yi","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China and Nanyang Technological University, Nanyang, Singapore"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China and Nanyang Technological University, Nanyang, Singapore","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I205237279","https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanfeng Ding","orcid":"https://orcid.org/0009-0000-4736-8134"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Ding","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390120","display_name":"Xiaoguang Liu","orcid":"https://orcid.org/0000-0002-9010-3278"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoguang Liu","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367433","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0003-0387-2501"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"College of C.S., Nankai-Baidu Joint Lab, TMCC, SysNet, DISSec, GTIISC, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101194582"],"corresponding_institution_ids":["https://openalex.org/I205237279","https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.4029,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8817692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3543","last_page":"3551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/lossless-compression","display_name":"Lossless compression","score":0.9120991230010986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7439488172531128},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6148706078529358},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5760112404823303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3637733459472656},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07164731621742249}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.9120991230010986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439488172531128},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6148706078529358},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5760112404823303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3637733459472656},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07164731621742249},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714655","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714655","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714655","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1454563993","display_name":null,"funder_award_id":"62272253","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1880386336","display_name":null,"funder_award_id":"China Scholarship Council (CSC)","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7931203216","display_name":null,"funder_award_id":"62272252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409657484.pdf","grobid_xml":"https://content.openalex.org/works/W4409657484.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4393207757"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2032414556","https://openalex.org/W2169871401","https://openalex.org/W2057878850"],"abstract_inverted_index":{"With":[0],"the":[1,5,7,25,56,122,138,144,153,167,178,187,195,200,203,210,213,263,266],"rapid":[2],"development":[3],"of":[4,10,140,174,180,202,212,244,251,260,265],"Internet,":[6],"huge":[8],"amount":[9],"Multi-Source":[11],"Data":[12],"(MSD)":[13],"brings":[14],"challenges":[15],"in":[16,38,66,73,121,143,177,216,242,249],"data":[17,22,39,48,196],"sharing":[18],"and":[19,68,86,105,170,225,247,262],"storing.":[20],"Lossless":[21],"compression":[23,75,84,154,163,168,211,245],"is":[24,206],"major":[26,112],"way":[27],"to":[28,61,126,151,165,190,208,254],"solve":[29,90],"those":[30,91],"problems.":[31],"Nowadays,":[32],"neural-network":[33],"technologies":[34],"bring":[35],"significant":[36],"advantage":[37],"modeling,":[40],"making":[41],"learning-based":[42,106,123,191,224],"lossless":[43,99],"compressors":[44,228],"(LLCs)":[45],"for":[46,129],"multi-source":[47],"have":[49,70],"emerged":[50],"continuously.":[51],"Compared":[52],"with":[53,221],"traditional":[54,227],"compressors,":[55],"LLCs":[57,79],"are":[58,269],"more":[59],"useful":[60],"catch":[62],"complex":[63],"redundancy":[64],"patterns":[65],"MSD,":[67],"thus":[69],"great":[71],"potential":[72],"enhancing":[74],"ratio.":[76],"However,":[77],"existing":[78],"still":[80],"suffer":[81],"from":[82],"unsatisfactory":[83],"ratios":[85],"lower":[87],"throughput.":[88],"To":[89],"problems,":[92],"we":[93],"propose":[94,116],"a":[95,117,160],"novel":[96],"universal":[97],"MSD":[98,130,189],"compressor":[100],"called":[101],"MSDZip":[102,220,239,261],"via":[103],"Stepwise-parallel":[104,161,184],"prediction":[107,124,192],"technologies,":[108],"it":[109],"introduces":[110],"two":[111],"designs:":[113],"1)":[114],"We":[115,158,218],"Local-Global-Deep":[118],"Mixing":[119,135],"block":[120,136],"module":[125,185],"establish":[127],"dependencies":[128],"symbols,":[131],"where":[132,199],"designed":[133],"Deep":[134],"solves":[137],"problem":[139,150],"unstable":[141],"weights":[142],"perceptual":[145],"layers":[146],"caused":[147],"by":[148],"cold-start":[149],"enhance":[152],"ratio":[155,246],"significantly.":[156],"2)":[157],"design":[159],"multi-GPU-accelerated":[162],"strategy":[164],"address":[166],"speed":[169],"graphics":[171],"memory":[172],"constraints":[173],"single":[175],"GPU":[176],"face":[179],"large-scale":[181],"data.":[182],"The":[183,234,257],"passes":[186],"source":[188,258],"model":[193,201],"through":[194],"chunking":[197],"strategy,":[198],"previous":[204],"chunk":[205,215],"used":[207],"guide":[209],"next":[214],"parallel.":[217],"compare":[219],"5":[222],"classical":[223],"6":[226],"on":[229],"12":[230],"well-studied":[231],"real-world":[232],"datasets.":[233],"experimental":[235,267],"results":[236],"demonstrate":[237],"that":[238],"optimizes":[240],"3.418%-69.874%":[241],"terms":[243,250],"31.171%-495.649%":[248],"throughput":[252],"compared":[253],"advanced":[255],"LLCs.":[256],"code":[259],"linkages":[264],"datasets":[268],"available":[270],"at":[271],"https://github.com/mhuidong/MSDZip.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}