{"id":"https://openalex.org/W4417439564","doi":"https://doi.org/10.1145/3774901.3778066","title":"ML Inference Scheduling with Predictable Latency","display_name":"ML Inference Scheduling with Predictable Latency","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417439564","doi":"https://doi.org/10.1145/3774901.3778066"},"language":"en","primary_location":{"id":"doi:10.1145/3774901.3778066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774901.3778066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3774901.3778066?download=true","source":null,"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 Middleware for Autonomous AIoT Systems in the Computing Continuum","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3774901.3778066?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101489943","display_name":"Haidong Zhao","orcid":"https://orcid.org/0009-0009-9864-5520"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Haidong Zhao","raw_affiliation_strings":["Inria, Paris, France and Sorbonne University, Paris, France"],"raw_orcid":"https://orcid.org/0009-0009-9864-5520","affiliations":[{"raw_affiliation_string":"Inria, Paris, France and Sorbonne University, Paris, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108812878","display_name":"Nikolaos Georgantas","orcid":"https://orcid.org/0000-0001-5704-4889"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nikolaos Georgantas","raw_affiliation_strings":["Inria, Paris, France"],"raw_orcid":"https://orcid.org/0000-0001-5704-4889","affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4253000020980835,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4253000020980835,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3206999897956848,"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/T14347","display_name":"Big Data and Digital Economy","score":0.045099999755620956,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6913999915122986},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6829000115394592},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6710000038146973},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5023999810218811},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5008000135421753},{"id":"https://openalex.org/keywords/compromise","display_name":"Compromise","score":0.4878000020980835},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.3749000132083893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583999872207642},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6913999915122986},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774901.3778066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774901.3778066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3774901.3778066?download=true","source":null,"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 Middleware for Autonomous AIoT Systems in the Computing Continuum","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.18725","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.18725","pdf_url":"https://arxiv.org/pdf/2512.18725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:HAL:hal-05431608v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05431608","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"MAIoT '25: Middleware for Autonomous AIoT Systems in the Computing Continuum in conjunction with the 26th ACM/IFIP International Middleware Conference (Middleware 2025), Dec 2025, Nashville, United States. pp.25-30, ⟨10.1145/3774901.3778066⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3774901.3778066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774901.3778066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3774901.3778066?download=true","source":null,"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 Middleware for Autonomous AIoT Systems in the Computing Continuum","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417439564.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2512971201","https://openalex.org/W2903485826","https://openalex.org/W3004615968","https://openalex.org/W3157306683","https://openalex.org/W3164445276","https://openalex.org/W3165292244","https://openalex.org/W4312443924","https://openalex.org/W4394944658","https://openalex.org/W4406014929"],"related_works":[],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"inference":[3,132],"serving":[4],"systems":[5],"can":[6],"schedule":[7],"requests":[8],"to":[9,14,95],"improve":[10],"GPU":[11,24,35],"utilization":[12,25],"and":[13,37,84,123],"meet":[15],"service":[16],"level":[17],"objectives":[18],"(SLOs)":[19],"or":[20,54],"deadlines.":[21],"However,":[22],"improving":[23],"may":[26,51,68,102],"compromise":[27,52],"latency-sensitive":[28],"scheduling,":[29,48],"as":[30],"concurrent":[31],"tasks":[32],"contend":[33],"for":[34,72],"resources":[36],"thereby":[38],"introduce":[39,45],"interference.":[40],"Given":[41],"that":[42],"interference":[43,59,90,120],"effects":[44],"unpredictability":[46],"in":[47,64,89],"neglecting":[49],"them":[50],"SLO":[53],"deadline":[55],"satisfaction.":[56],"Nevertheless,":[57],"existing":[58,119],"prediction":[60,99,121],"approaches":[61,122],"remain":[62],"limited":[63],"several":[65],"respects,":[66],"which":[67,79,101],"restrict":[69],"their":[70,87],"usefulness":[71],"scheduling.":[73,133],"First,":[74],"they":[75,93],"are":[76],"often":[77],"coarse-grained,":[78],"ignores":[80],"runtime":[81],"co-location":[82],"dynamics":[83],"thus":[85],"restricts":[86],"accuracy":[88],"prediction.":[91],"Second,":[92],"tend":[94],"use":[96],"a":[97],"static":[98],"model,":[100],"not":[103],"effectively":[104],"cope":[105],"with":[106],"different":[107],"workload":[108],"characteristics.":[109],"To":[110],"this":[111],"end,":[112],"we":[113],"evaluate":[114],"the":[115],"potential":[116],"limitations":[117],"of":[118],"outline":[124],"our":[125],"ongoing":[126],"work":[127],"toward":[128],"achieving":[129],"efficient":[130],"ML":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-12-17T00:00:00"}