{"id":"https://openalex.org/W7204577684","doi":"https://doi.org/10.48550/arxiv.2608.27244","title":"Compositional Online Learning for Semantic Data Processing Systems","display_name":"Compositional Online Learning for Semantic Data Processing Systems","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204577684","doi":"https://doi.org/10.48550/arxiv.2608.27244"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27244","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27244","pdf_url":"https://arxiv.org/pdf/2608.27244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062664935","display_name":"Pawe\u0142 Liskowski","orcid":"https://orcid.org/0000-0002-8165-748X","observed_orcids":["https://orcid.org/0000-0002-8165-748X"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liskowski, Pawe\u0142","raw_affiliation_strings":["Snowflake Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake Inc","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020064057","display_name":"Fuheng Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Fuheng","raw_affiliation_strings":["Snowflake Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake Inc","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135466293","display_name":"Benjamin Han","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han, Benjamin","raw_affiliation_strings":["Snowflake Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake Inc","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111177928","display_name":"Anupam Datta","orcid":"https://orcid.org/0000-0002-2751-068X","observed_orcids":["https://orcid.org/0000-0002-2751-068X"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Datta, Anupam","raw_affiliation_strings":["Snowflake Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake Inc","institution_ids":["https://openalex.org/I4400600931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087105600","display_name":"Dimitris Tsirogiannis","orcid":"https://orcid.org/0009-0002-6826-1584","observed_orcids":["https://orcid.org/0009-0002-6826-1584"]},"institutions":[{"id":"https://openalex.org/I4400600931","display_name":"Snowflake Inc. (United States)","ror":"https://ror.org/04vrpfw15","country_code":"US","type":"company","lineage":["https://openalex.org/I4400600931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsirogiannis, Dimitris","raw_affiliation_strings":["Snowflake Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snowflake Inc","institution_ids":["https://openalex.org/I4400600931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4400600931"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.002899999963119626,"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/T11106","display_name":"Data Management and Algorithms","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/adaptive-query-processing","display_name":"adaptive query processing","score":0.9369999766349792},{"id":"https://openalex.org/keywords/memoization","display_name":"memoization","score":0.7089999914169312},{"id":"https://openalex.org/keywords/selectivity-estimation","display_name":"selectivity estimation","score":0.625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8471999764442444},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C79516417","wikidata":"https://www.wikidata.org/wiki/Q1376168","display_name":"Memoization","level":4,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.4007999897003174},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C98199447","wikidata":"https://www.wikidata.org/wiki/Q2445044","display_name":"Materialized view","level":4,"score":0.25360000133514404},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27244","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27244","pdf_url":"https://arxiv.org/pdf/2608.27244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27244","doi":"https://doi.org/10.48550/arxiv.2608.27244","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27244","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27244","pdf_url":"https://arxiv.org/pdf/2608.27244","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204577684.pdf","grobid_xml":"https://content.openalex.org/works/W7204577684.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W4376122773","https://openalex.org/W4413978072","https://openalex.org/W4413979874","https://openalex.org/W4416527932","https://openalex.org/W4416682780","https://openalex.org/W7148563108","https://openalex.org/W7156919061","https://openalex.org/W7164047557"],"related_works":["https://openalex.org/W7168517421","https://openalex.org/W7202135484","https://openalex.org/W7171517964","https://openalex.org/W7109229324","https://openalex.org/W7135229600","https://openalex.org/W7134059465","https://openalex.org/W7214352038","https://openalex.org/W7154380691","https://openalex.org/W4416854088","https://openalex.org/W4391671103"],"abstract_inverted_index":{"An":[0],"LLM":[1,30,73,93,146,186],"call":[2,40,94],"in":[3,102,152],"a":[4,21,43,50,96,134,158,181,202,219],"semantic":[5,103],"data":[6,104],"processing":[7,105],"system":[8],"is":[9],"expensive":[10],"enough":[11,18],"to":[12,19,62,65,180,196,218],"dominate":[13],"query":[14,36,56],"cost,":[15,37],"yet":[16],"slow":[17],"hide":[20],"CPU-side":[22],"learner's":[23],"update":[24,128],"behind":[25],"its":[26,114],"round-trip.":[27,85,147],"In":[28],"production,":[29],"compute":[31],"accounts":[32],"for":[33,98],"$80-90\\%$":[34],"of":[35,53,184],"and":[38,78,112,126,130,166,213],"each":[39,140,177],"costs":[41],"$10^5-10^7\\times$":[42],"relational":[44],"predicate.":[45],"The":[46,118],"latency":[47],"window":[48],"inverts":[49],"design":[51,119],"constraint":[52],"classical":[54],"adaptive":[55],"processing,":[57],"where":[58],"online":[59,89,162,168],"learners":[60],"had":[61],"stay":[63],"lightweight":[64],"avoid":[66],"dominating":[67],"the":[68,84,92,131,144,190,208],"predicates":[69],"they":[70],"optimize.":[71],"At":[72],"latency,":[74],"per-call":[75,163],"gradient":[76],"steps":[77],"per-batch":[79,169],"threshold":[80],"solves":[81],"fit":[82],"inside":[83,143],"We":[86],"develop":[87],"compositional":[88],"learning":[90,136,178,192],"at":[91,207],"boundary:":[95],"framework":[97],"combining":[99],"online-learning":[100],"components":[101,132,193],"systems.":[106],"Each":[107],"component":[108,179],"makes":[109],"execution-time":[110],"decisions":[111],"refines":[113],"learned":[115],"artifacts":[116],"online.":[117],"space":[120],"spans":[121],"two":[122,191],"axes,":[123],"decision":[124],"granularity":[125],"learner":[127],"cadence,":[129],"share":[133],"single":[135],"pattern":[137],"that":[138],"hides":[139],"trainer":[141],"step":[142],"next":[145],"A":[148,172],"production":[149],"case":[150],"study":[151],"Cortex":[153],"AISQL":[154],"composes":[155],"three":[156],"components:":[157],"memoization":[159],"layer,":[160],"an":[161,167,197],"filter-ordering":[164],"learner,":[165],"cascade-routing":[170],"learner.":[171],"conditional":[173],"cost":[174],"decomposition":[175],"assigns":[176],"distinct":[182],"factor":[183],"per-row":[185],"cost.":[187],"Under":[188],"independence,":[189],"compose":[194],"multiplicatively":[195],"$11.4\\times$":[198],"upper":[199],"bound":[200],"on":[201],"representative":[203],"conjunction-filter":[204],"workload.":[205],"Self-selection":[206],"cascade":[209],"boundary,":[210],"sample-budget":[211],"shrinkage,":[212],"selectivity-estimation":[214],"drift":[215],"reduce":[216],"it":[217],"realistic":[220],"figure":[221],"near":[222],"$8\\times$.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}