{"id":"https://openalex.org/W7161179029","doi":"https://doi.org/10.1109/dcc66757.2026.00107","title":"Improving Compression Ratio of Lossy Compression on HPC Datasets via Modeling-Based Arithmetic Coding","display_name":"Improving Compression Ratio of Lossy Compression on HPC Datasets via Modeling-Based Arithmetic Coding","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7161179029","doi":"https://doi.org/10.1109/dcc66757.2026.00107"},"language":null,"primary_location":{"id":"doi:10.1109/dcc66757.2026.00107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","raw_type":"proceedings-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/A5136152069","display_name":"Zhichao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhichao Yang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136112805","display_name":"Xiangyu Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zou","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091356951","display_name":"Shihao Wang","orcid":"https://orcid.org/0009-0001-9960-6998"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihao Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136104160","display_name":"Hao Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Hu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136097711","display_name":"Wen Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen,Shenzhen,China,518055","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5136152069"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94921054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"480","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.7226999998092651,"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":0.7226999998092651,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.11110000312328339,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.039400000125169754,"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/arithmetic-coding","display_name":"Arithmetic coding","score":0.6990000009536743},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.689300000667572},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6373999714851379},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5078999996185303},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5022000074386597},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5006999969482422},{"id":"https://openalex.org/keywords/context-adaptive-binary-arithmetic-coding","display_name":"Context-adaptive binary arithmetic coding","score":0.48429998755455017}],"concepts":[{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.6990000009536743},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.689300000667572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6615999937057495},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6373999714851379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.51910001039505},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5078999996185303},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5006999969482422},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.3644999861717224},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.32989999651908875},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dcc66757.2026.00107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6511555910110474,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"HPC":[0,80,231],"applications":[1],"generate":[2],"massive":[3],"amounts":[4],"of":[5,97,158,161,221],"data":[6,29,61],"that":[7,45,142,197,214],"impose":[8],"significant":[9],"burdens":[10],"on":[11,42,109,128,230],"both":[12],"storage":[13,145],"and":[14,83,93,101,170,182,199,209,237],"I/O":[15,55],"systems.":[16],"Although":[17],"lossy":[18],"compressors":[19,103],"have":[20],"been":[21],"widely":[22],"adopted":[23],"in":[24,60],"this":[25],"scenario":[26],"to":[27,35,87,132,168,205],"reduce":[28,133],"volume,":[30],"the":[31,57,77,89,156,159],"SOTA":[32],"approach":[33],"fails":[34],"fully":[36],"exploit":[37],"redundancy":[38],"because":[39],"it":[40],"relies":[41],"separate":[43],"techniques":[44],"operate":[46],"at":[47],"incompatible":[48],"granularities.":[49],"Their":[50],"suboptimal":[51],"compression":[52,68,90,192,198,218],"ratios":[53],"leave":[54],"as":[56,112,135,234],"dominant":[58],"bottleneck":[59],"dumps/loads.":[62],"Therefore,":[63],"we":[64],"propose":[65],"MAC,":[66],"a":[67,186,217],"framework":[69],"built":[70],"upon":[71],"existing":[72],"SZ":[73,113],"compressor.":[74],"It":[75],"leverages":[76],"alignment":[78],"between":[79],"system":[81,151],"characteristics":[82],"modeling-based":[84],"arithmetic":[85,121],"coding":[86,100],"balance":[88],"ratio":[91,219],"improvement":[92,220],"time":[94],"cost.":[95],"Instead":[96],"applying":[98],"Huffman":[99],"dictionary-based":[102],"like":[104],"zstd":[105],"or":[106],"gzip":[107],"sequentially":[108],"quantization":[110,130,163],"factors":[111,131,137],"does,":[114],"MAC":[115,124,189],"replaces":[116],"them":[117,184],"with":[118,155,178],"an":[119],"adaptive":[120],"encoder.":[122],"Specifically,":[123],"first":[125],"employs":[126],"bit-packing":[127],"incoming":[129],"overhead,":[134],"these":[136],"are":[138],"typically":[139],"small":[140],"enough":[141,204],"standard":[143],"4-byte":[144],"would":[146],"impede":[147],"processing":[148],"efficiency.":[149],"The":[150],"then":[152],"constructs":[153],"context":[154],"knowledge":[157],"length":[160],"each":[162],"factor,":[164],"utilizing":[165],"hash":[166],"tables":[167],"store":[169],"retrieve":[171],"historical":[172],"occurrences.":[173],"By":[174],"leveraging":[175],"two":[176],"models":[177],"distinct":[179],"prefix-matching":[180],"strategies":[181],"integrating":[183],"via":[185],"logistic":[187],"mixer,":[188],"yields":[190],"substantial":[191],"gains.":[193],"This":[194],"architecture":[195],"ensures":[196],"decompression":[200],"latencies":[201],"remain":[202],"low":[203],"accelerate":[206],"overall":[207],"dump":[208],"load":[210],"operations.":[211],"Experiments":[212],"show":[213],"MACSZ":[215],"achieves":[216],"over":[222],"25%,":[223],"which":[224],"translates":[225],"directly":[226],"into":[227],"enhanced":[228],"throughput":[229],"cluster":[232],"architectures":[233],"Fig":[235],"1":[236],"2":[238],"demonstrate.":[239]},"counts_by_year":[],"updated_date":"2026-05-16T06:04:12.930555","created_date":"2026-05-15T00:00:00"}