{"id":"https://openalex.org/W4412038617","doi":"https://doi.org/10.1145/3719276.3725190","title":"Accordion: A malleable pipeline scheduling approach for adaptive SLO-aware inference serving","display_name":"Accordion: A malleable pipeline scheduling approach for adaptive SLO-aware inference serving","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4412038617","doi":"https://doi.org/10.1145/3719276.3725190"},"language":"en","primary_location":{"id":"doi:10.1145/3719276.3725190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3725190","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3725190","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3725190","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081394062","display_name":"Pirah Noor Soomro","orcid":"https://orcid.org/0000-0001-8654-3249"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Pirah Noor Soomro","raw_affiliation_strings":["Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-8654-3249","affiliations":[{"raw_affiliation_string":"Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057776164","display_name":"\u039d\u03b9\u03ba\u03ad\u03bb\u03b1 \u03a0\u03b1\u03c0\u03b1\u03b4\u03bf\u03c0\u03bf\u03cd\u03bb\u03bf\u03c5","orcid":"https://orcid.org/0000-0003-2141-5654"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nikela Papadopoulou","raw_affiliation_strings":["University of Glasgow, Glasgow, Scotland UK"],"raw_orcid":"https://orcid.org/0000-0003-2141-5654","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, Scotland UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074518408","display_name":"Miquel Peric\u00e0s","orcid":"https://orcid.org/0000-0002-7583-6609"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Miquel Peric\u00e0s","raw_affiliation_strings":["Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-7583-6609","affiliations":[{"raw_affiliation_string":"Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14928788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.986299991607666,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.986299991607666,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9807999730110168,"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/T13553","display_name":"Age of Information Optimization","score":0.9751999974250793,"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/computer-science","display_name":"Computer science","score":0.8043014407157898},{"id":"https://openalex.org/keywords/accordion","display_name":"Accordion","score":0.7591992616653442},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5795656442642212},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5789185762405396},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.476589173078537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35596948862075806},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1708633303642273},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12156620621681213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09023919701576233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043014407157898},{"id":"https://openalex.org/C87732919","wikidata":"https://www.wikidata.org/wiki/Q3536726","display_name":"Accordion","level":2,"score":0.7591992616653442},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5795656442642212},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5789185762405396},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.476589173078537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35596948862075806},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1708633303642273},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12156620621681213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09023919701576233},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3719276.3725190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3725190","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3725190","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:356744","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/76144.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.1145/3719276.3725190","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3719276.3725190","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3719276.3725190","source":null,"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G200040415","display_name":"European, extendable, energy-efficient, energetic, embedded, extensible, Processor Ecosystem","funder_award_id":"956702","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G979276111","display_name":"PRIDE: Principer f\u00f6r ber\u00e4knande minnesenheter","funder_award_id":"CHI19-0048","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412038617.pdf","grobid_xml":"https://content.openalex.org/works/W4412038617.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2176686728","https://openalex.org/W2604514113","https://openalex.org/W2606722458","https://openalex.org/W2664267452","https://openalex.org/W2794670651","https://openalex.org/W2801090658","https://openalex.org/W2887117815","https://openalex.org/W2944614352","https://openalex.org/W2969388332","https://openalex.org/W2972087877","https://openalex.org/W2982157693","https://openalex.org/W3011434423","https://openalex.org/W3016842236","https://openalex.org/W3026530461","https://openalex.org/W3043433718","https://openalex.org/W3130689885","https://openalex.org/W3158444059","https://openalex.org/W3186289964","https://openalex.org/W3210617645","https://openalex.org/W4226212055","https://openalex.org/W4231332361","https://openalex.org/W4236491543","https://openalex.org/W4280633167","https://openalex.org/W4294904165","https://openalex.org/W4386106708","https://openalex.org/W4394892775"],"related_works":["https://openalex.org/W2358431862","https://openalex.org/W2617599698","https://openalex.org/W2382550486","https://openalex.org/W2374999260","https://openalex.org/W4248732321","https://openalex.org/W4391392579","https://openalex.org/W3007134999","https://openalex.org/W2994131083","https://openalex.org/W2354373329","https://openalex.org/W4399084107"],"abstract_inverted_index":{"With":[0],"the":[1,38,83,106,121,145,157,162,173,184],"rising":[2],"demand":[3],"for":[4,85],"machine":[5],"learning-based":[6],"applications,":[7],"efficient":[8],"and":[9,35,186],"cost-effective":[10],"inference":[11,46,89,93,165,170],"serving":[12,47],"systems":[13,17],"have":[14],"become":[15],"imperative.These":[16],"are":[18],"tasked":[19],"with":[20],"meeting":[21,131],"customer":[22],"requirements":[23],"outlined":[24],"by":[25,44,104],"Service":[26],"Level":[27],"Objectives":[28],"(SLOs),":[29],"encompassing":[30],"model":[31],"accuracy,":[32],"response":[33,62],"time,":[34],"cost":[36],"considerations.Despite":[37],"adoption":[39],"of":[40,142,148,159,194],"proactive":[41],"scheduling":[42,73],"techniques":[43,74],"modern":[45],"systems,":[48],"dynamic":[49],"factors":[50],"such":[51,59],"as":[52,60],"fluctuating":[53],"query":[54,149,166],"patterns":[55],"still":[56],"pose":[57],"challenges":[58],"delayed":[61],"time.To":[63],"address":[64],"these,":[65],"we":[66,95],"propose":[67],"an":[68,139],"adaptive":[69],"solution":[70,175],"leveraging":[71],"SLOaware":[72],"to":[75,81,109,112,152,167,183],"optimize":[76],"resource":[77,99,107],"allocation.Our":[78],"approach":[79],"aims":[80],"minimize":[82],"need":[84],"additional":[86],"resources":[87,127,163],"per":[88,164,196],"service.By":[90],"introducing":[91],"malleable":[92],"pipelines,":[94],"enhance":[96],"flexibility":[97],"in":[98,144,172,192],"allocation":[100],"during":[101],"peak":[102],"loads":[103],"readjusting":[105],"assignment":[108],"processing":[110],"pipelines":[111],"accommodate":[113,168],"maximum":[114],"possible":[115],"queries":[116,171,179,195],"dynamically.Our":[117],"findings":[118],"indicate":[119],"that":[120],"proposed":[122],"scheduler":[123],"effectively":[124],"utilizes":[125],"system":[126,190],"throughout":[128],"execution":[129],"while":[130],"most":[132],"SLOs":[133],"(4.2\u00d7":[134],"less":[135],"SLO":[136],"violations).We":[137],"observe":[138],"average":[140,181],"reduction":[141],"1.6\u00d7":[143,188],"endto-end":[146],"latency":[147],"processing,":[150],"compared":[151,182],"baseline":[153],"methods.We":[154],"also":[155],"demonstrate":[156],"impact":[158],"dynamically":[160],"reducing":[161],"more":[169,178],"system.Our":[174],"accommodates":[176],"1.4\u00d7":[177],"on":[180,198],"baselines":[185],"achieves":[187],"higher":[189],"throughput":[191],"terms":[193],"second":[197],"average.":[199]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}