{"id":"https://openalex.org/W4220938834","doi":"https://doi.org/10.1145/3514221.3517848","title":"Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines","display_name":"Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4220938834","doi":"https://doi.org/10.1145/3514221.3517848"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517848","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.08679","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113018344","display_name":"Alexander Isenko","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Isenko","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060499098","display_name":"Ruben Mayer","orcid":"https://orcid.org/0000-0001-9870-7466"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruben Mayer","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078345536","display_name":"Jeffrey Jedele","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jeffrey Jedele","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072791865","display_name":"Hans\u2010Arno Jacobsen","orcid":"https://orcid.org/0000-0003-0813-0101"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hans-Arno Jacobsen","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113018344"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.4956,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88083747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1825","last_page":"1839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9988999962806702,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8559991121292114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114420771598816},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7216793894767761},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.716193437576294},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6683483719825745},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.666046142578125},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.622153103351593},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5733035206794739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5092445611953735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46308380365371704},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.42821216583251953},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4073677062988281},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35426920652389526},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1974772810935974},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12655770778656006},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09265360236167908},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07704794406890869}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8559991121292114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114420771598816},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7216793894767761},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.716193437576294},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6683483719825745},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.666046142578125},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.622153103351593},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5733035206794739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5092445611953735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46308380365371704},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.42821216583251953},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4073677062988281},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35426920652389526},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1974772810935974},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12655770778656006},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09265360236167908},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07704794406890869},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514221.3517848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517848","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2202.08679","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.08679","pdf_url":"https://arxiv.org/pdf/2202.08679","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.08679","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.08679","pdf_url":"https://arxiv.org/pdf/2202.08679","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1566289585","https://openalex.org/W1576445103","https://openalex.org/W1743861851","https://openalex.org/W1777016212","https://openalex.org/W1791987072","https://openalex.org/W1825216778","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1939575207","https://openalex.org/W2015585187","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2119885577","https://openalex.org/W2140196014","https://openalex.org/W2142265837","https://openalex.org/W2145607950","https://openalex.org/W2155904486","https://openalex.org/W2157963512","https://openalex.org/W2183341477","https://openalex.org/W2189465200","https://openalex.org/W2194775991","https://openalex.org/W2342249984","https://openalex.org/W2615044227","https://openalex.org/W2743948853","https://openalex.org/W2795087227","https://openalex.org/W2900042580","https://openalex.org/W2900901189","https://openalex.org/W2914040074","https://openalex.org/W2914304175","https://openalex.org/W2931364255","https://openalex.org/W2951947775","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2991082611","https://openalex.org/W2999905431","https://openalex.org/W3004495293","https://openalex.org/W3006973014","https://openalex.org/W3015963989","https://openalex.org/W3022863654","https://openalex.org/W3102254513","https://openalex.org/W3106772683","https://openalex.org/W3112593626","https://openalex.org/W3138021606","https://openalex.org/W3138303811","https://openalex.org/W4243236934","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2989490741","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064","https://openalex.org/W3092506759"],"abstract_inverted_index":{"Preprocessing":[0],"pipelines":[1],"in":[2,58,82],"deep":[3,84],"learning":[4,85],"aim":[5],"to":[6,11,60],"provide":[7],"sufficient":[8],"data":[9,56,73],"throughput":[10,26],"keep":[12],"the":[13,25,49,52],"training":[14,28,55],"processes":[15,29],"busy.":[16],"Maximizing":[17],"resource":[18],"utilization":[19],"is":[20,65],"becoming":[21,78],"more":[22],"challenging":[23],"as":[24],"of":[27,54,70],"increases":[30],"with":[31],"hardware":[32],"innovations":[33],"(e.g.,":[34],"faster":[35],"GPUs,":[36],"TPUs,":[37],"and":[38,40,75],"inter-connects)":[39],"advanced":[41],"parallelization":[42],"techniques":[43],"that":[44],"yield":[45],"better":[46],"scalability.":[47],"At":[48],"same":[50],"time,":[51],"amount":[53],"needed":[57],"order":[59],"train":[61],"increasingly":[62],"complex":[63],"models":[64],"growing.":[66],"As":[67],"a":[68,79],"consequence":[69],"this":[71],"development,":[72],"preprocessing":[74],"provisioning":[76],"are":[77],"severe":[80],"bottleneck":[81],"end-to-end":[83],"pipelines.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}