{"id":"https://openalex.org/W7133326275","doi":"https://doi.org/10.48550/arxiv.2603.02075","title":"Trident: Adaptive Scheduling for Heterogeneous Multimodal Data Pipelines","display_name":"Trident: Adaptive Scheduling for Heterogeneous Multimodal Data Pipelines","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133326275","doi":"https://doi.org/10.48550/arxiv.2603.02075"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02075","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02075","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127889387","display_name":"Ding Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037180684","display_name":"Zhuangzhuang Zhou","orcid":"https://orcid.org/0000-0003-1982-2031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhuangzhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128033719","display_name":"Long Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128002263","display_name":"Binhang Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Binhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.14249999821186066,"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"}},"topics":[{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.14249999821186066,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.07599999755620956,"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":0.05959999933838844,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6079000234603882},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5242000222206116},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.427700012922287},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.38260000944137573},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.36820000410079956},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.3643999993801117},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.358599990606308},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3359000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678999900817871},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.47440001368522644},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4729999899864197},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.358599990606308},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C2778047078","wikidata":"https://www.wikidata.org/wiki/Q82299449","display_name":"Tardiness","level":4,"score":0.2565000057220459},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02075","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02075","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02075","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6249032020568848,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1,53],"adoption":[2],"of":[3],"large":[4],"language":[5],"models":[6,10],"and":[7,29,48,56,126,135,152,158,172,201],"multimodal":[8,13,85],"foundation":[9],"has":[11],"made":[12],"data":[14],"preparation":[15],"pipelines":[16,21,86],"critical":[17],"AI":[18],"infrastructure.":[19],"These":[20],"interleave":[22],"CPU-heavy":[23],"preprocessing":[24],"with":[25,114,179,212],"accelerator-backed":[26],"(GPU/NPU/TPU)":[27],"inference":[28],"produce":[30],"massive":[31],"intermediate":[32],"artifacts.":[33],"Achieving":[34],"high":[35],"throughput":[36,106,190],"is":[37],"difficult":[38],"because":[39],"workloads":[40],"are":[41],"highly":[42],"non-stationary:":[43],"regime":[44],"shifts,":[45],"input-dependent":[46],"inference,":[47],"transient":[49],"memory":[50],"spikes":[51],"cause":[52],"performance":[54],"fluctuations":[55],"out-of-memory":[57],"(OOM)":[58],"failures.":[59],"Existing":[60],"schedulers":[61],"typically":[62],"rely":[63],"on":[64,87,184,195,203],"threshold-based":[65],"autoscaling":[66],"or":[67],"assume":[68],"synchronous,":[69],"homogeneous":[70],"operators,":[71],"leading":[72],"to":[73,131,146,175,193],"poor":[74],"efficiency.":[75],"We":[76],"present":[77],"Trident,":[78],"an":[79,99,118],"adaptive":[80],"scheduling":[81,138],"framework":[82],"for":[83,107,162,216],"heterogeneous":[84,156],"fixed-resource":[88],"clusters.":[89],"Trident":[90,187],"closes":[91],"the":[92,180],"loop":[93],"across":[94],"three":[95],"coupled":[96],"layers:":[97],"(i)":[98],"observation":[100],"layer":[101,120,139],"that":[102,121,140],"estimates":[103,177],"per-operator":[104],"sustainable":[105],"asynchronous":[108],"operators":[109],"via":[110,165],"Gaussian":[111],"Process":[112],"regression":[113],"anomaly":[115],"filtering;":[116],"(ii)":[117],"adaptation":[119],"detects":[122],"workload":[123],"shifts":[124],"online":[125,217],"performs":[127],"memory-constrained":[128],"Bayesian":[129],"optimization":[130],"recommend":[132],"OOM-safe":[133],"configurations;":[134],"(iii)":[136],"a":[137,142,196,204,209],"solves":[141],"mixed-integer":[143],"linear":[144],"program":[145],"jointly":[147],"optimize":[148],"operator":[149],"parallelism,":[150],"placement,":[151],"configuration":[153],"transitions":[154],"under":[155],"compute":[157],"bandwidth":[159],"constraints,":[160],"accounting":[161],"cold-start":[163],"overhead":[164,214],"rolling":[166],"updates.":[167],"Decisions":[168],"trigger":[169],"sample":[170],"invalidation":[171],"model":[173],"refresh":[174],"keep":[176],"consistent":[178],"active":[181],"configuration.":[182],"Implemented":[183],"Ray":[185],"Data,":[186],"improves":[188],"end-to-end":[189],"by":[191],"up":[192],"2.01x":[194],"document":[197],"curation":[198,206],"(PDF)":[199],"pipeline":[200,207],"1.88x":[202],"video":[205],"over":[208],"static":[210],"baseline,":[211],"low":[213],"suitable":[215],"re-optimization.":[218]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-04T00:00:00"}