{"id":"https://openalex.org/W4410049497","doi":"https://doi.org/10.1145/3676151.3719373","title":"PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time","display_name":"PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time","publication_year":2025,"publication_date":"2025-05-03","ids":{"openalex":"https://openalex.org/W4410049497","doi":"https://doi.org/10.1145/3676151.3719373"},"language":"en","primary_location":{"id":"doi:10.1145/3676151.3719373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719373","pdf_url":null,"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 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3676151.3719373","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067849247","display_name":"Alireza Pourali","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Alireza Pourali","raw_affiliation_strings":["York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0001-9387-2099","affiliations":[{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115616156","display_name":"Arian Boukani","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arian Boukani","raw_affiliation_strings":["York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0009-0006-8871-9256","affiliations":[{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003994483","display_name":"Hamzeh Khazaei","orcid":"https://orcid.org/0000-0001-5439-8024"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hamzeh Khazaei","raw_affiliation_strings":["York University, Toronto, Canada"],"raw_orcid":"https://orcid.org/0000-0001-5439-8024","affiliations":[{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067849247"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07106953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9968000054359436,"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":0.9968000054359436,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9851999878883362,"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/T10028","display_name":"Topic Modeling","score":0.9837999939918518,"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/computer-science","display_name":"Computer science","score":0.7982019782066345},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7127928137779236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6494665741920471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6054981350898743},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49321049451828003},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4037379026412964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982019782066345},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7127928137779236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6494665741920471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6054981350898743},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49321049451828003},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4037379026412964},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676151.3719373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719373","pdf_url":null,"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 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676151.3719373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676151.3719373","pdf_url":null,"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 16th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2493916176","https://openalex.org/W2560674852","https://openalex.org/W2606722458","https://openalex.org/W2734941459","https://openalex.org/W2903557836","https://openalex.org/W2946408574","https://openalex.org/W2981852735","https://openalex.org/W3081659545","https://openalex.org/W3121689374","https://openalex.org/W3135013702","https://openalex.org/W3183603480","https://openalex.org/W4224308101","https://openalex.org/W4286300788","https://openalex.org/W4288089799","https://openalex.org/W4395483140","https://openalex.org/W4396686575","https://openalex.org/W4396709386","https://openalex.org/W6782268329","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W4387369504","https://openalex.org/W3082895349"],"abstract_inverted_index":{"Training":[0],"deep":[1],"learning":[2],"models,":[3],"particularly":[4],"Transformer-based":[5],"architectures":[6],"such":[7],"as":[8],"Large":[9],"Language":[10],"Models":[11],"(LLMs),":[12],"demands":[13],"substantial":[14],"computational":[15,59],"resources":[16],"and":[17,24,66,99,120,128,134],"extended":[18],"training":[19,54,80,136],"periods.":[20],"While":[21],"optimal":[22,124],"configuration":[23],"infrastructure":[25],"selection":[26],"can":[27,122],"significantly":[28],"reduce":[29],"associated":[30],"costs,":[31],"this":[32,49],"optimization":[33,50,55],"requires":[34],"preliminary":[35],"analysis":[36],"tools.":[37],"This":[38,91],"paper":[39],"introduces":[40],"PreNeT,":[41,118],"a":[42,94],"novel":[43,88],"predictive":[44],"framework":[45,92],"designed":[46],"to":[47,77,97,131,145,152],"address":[48],"challenge.":[51],"PreNeT":[52,73,142],"facilitates":[53],"by":[56],"integrating":[57],"comprehensive":[58],"metrics,":[60],"including":[61,87],"layer-specific":[62],"parameters,":[63],"arithmetic":[64],"operations":[65],"memory":[67],"utilization.":[68],"A":[69],"key":[70],"feature":[71],"of":[72,104,117],"is":[74],"its":[75],"capacity":[76],"accurately":[78],"predict":[79],"duration":[81],"on":[82],"previously":[83],"unexamined":[84],"hardware":[85,129],"infrastructures,":[86],"accelerator":[89],"architectures.":[90],"employs":[93],"sophisticated":[95],"approach":[96],"capture":[98],"analyze":[100],"the":[101],"distinct":[102],"characteristics":[103],"various":[105],"neural":[106],"network":[107],"layers,":[108],"thereby":[109],"enhancing":[110],"existing":[111],"prediction":[112,149],"methodologies.":[113],"Through":[114],"proactive":[115],"implementation":[116],"researchers":[119],"practitioners":[121],"determine":[123],"configurations,":[125],"parameter":[126],"settings,":[127],"specifications":[130],"maximize":[132],"cost-efficiency":[133],"minimize":[135],"duration.":[137],"Experimental":[138],"results":[139],"demonstrate":[140],"that":[141],"achieves":[143],"up":[144],"72%":[146],"improvement":[147],"in":[148],"accuracy":[150],"compared":[151],"contemporary":[153],"state-of-the-art":[154],"frameworks.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}