{"id":"https://openalex.org/W4417167910","doi":"https://doi.org/10.1109/tpds.2026.3708042","title":"Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems","display_name":"Leveraging Neural Graph Compilers in Machine Learning Research for Edge-Cloud Systems","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W4417167910","doi":"https://doi.org/10.1109/tpds.2026.3708042"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2026.3708042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3708042","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpds.2026.3708042","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073074473","display_name":"Alireza Furutanpey","orcid":"https://orcid.org/0000-0001-5621-7899"},"institutions":[{"id":"https://openalex.org/I4210128228","display_name":"Eli Lilly (Spain)","ror":"https://ror.org/033911096","country_code":"ES","type":"company","lineage":["https://openalex.org/I168537998","https://openalex.org/I4210128228"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alireza Furutanpey","raw_affiliation_strings":["Coovally, 08018 Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-5621-7899","affiliations":[{"raw_affiliation_string":"Coovally, 08018 Barcelona, Spain","institution_ids":["https://openalex.org/I4210128228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042544547","display_name":"Carmen Walser","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Carmen Walser","raw_affiliation_strings":["Distributed Systems Group, TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Systems Group, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058231798","display_name":"Philipp Raith","orcid":"https://orcid.org/0000-0003-3293-9437"},"institutions":[{"id":"https://openalex.org/I4210128228","display_name":"Eli Lilly (Spain)","ror":"https://ror.org/033911096","country_code":"ES","type":"company","lineage":["https://openalex.org/I168537998","https://openalex.org/I4210128228"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Philipp Raith","raw_affiliation_strings":["Coovally, 08018 Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-3293-9437","affiliations":[{"raw_affiliation_string":"Coovally, 08018 Barcelona, Spain","institution_ids":["https://openalex.org/I4210128228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020923950","display_name":"Pantelis A. Frangoudis","orcid":"https://orcid.org/0000-0001-6901-7714"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Pantelis A. Frangoudis","raw_affiliation_strings":["Distributed Systems Group, TU Wien, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0001-6901-7714","affiliations":[{"raw_affiliation_string":"Distributed Systems Group, TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004847496","display_name":"Schahram Dustdar","orcid":"https://orcid.org/0000-0001-6872-8821"},"institutions":[{"id":"https://openalex.org/I11932220","display_name":"Instituci\u00f3 Catalana de Recerca i Estudis Avan\u00e7ats","ror":"https://ror.org/0371hy230","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I11932220"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Schahram Dustdar","raw_affiliation_strings":["ICREA, 08010 Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6872-8821","affiliations":[{"raw_affiliation_string":"ICREA, 08010 Barcelona, Spain","institution_ids":["https://openalex.org/I11932220"]}]}],"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":0.01896498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"9","first_page":"2065","last_page":"2077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.48249998688697815,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.48249998688697815,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0949999988079071,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07500000298023224,"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/compiler","display_name":"Compiler","score":0.7775999903678894},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.741100013256073},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7059000134468079},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.505299985408783},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4772999882698059},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4564000070095062},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4147000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174999952316284},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7775999903678894},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.741100013256073},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7059000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5361999869346619},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49720001220703125},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4147000014781952},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.39719998836517334},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C88977235","wikidata":"https://www.wikidata.org/wiki/Q787114","display_name":"Abstract machine","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C8767382","wikidata":"https://www.wikidata.org/wiki/Q1058454","display_name":"Dynamic compilation","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpds.2026.3708042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3708042","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.20198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20198","pdf_url":"https://arxiv.org/pdf/2504.20198","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2504.20198","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.20198","pdf_url":"https://arxiv.org/pdf/2504.20198","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":"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":"doi:10.48550/arxiv.2504.20198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.20198","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1109/tpds.2026.3708042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2026.3708042","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,97],"comprehensive":[4],"evaluation":[5],"of":[6],"neural":[7,62],"network":[8],"graph":[9,53],"compilers":[10,54,75],"across":[11,136],"heterogeneous":[12,137],"hardware":[13,138],"platforms,":[14],"addressing":[15],"the":[16,111,124],"critical":[17],"gap":[18,112],"between":[19,37,113],"theoretical":[20],"optimization":[21,134],"techniques":[22],"and":[23,64,116],"practical":[24,117],"deployment":[25,118],"scenarios.":[26],"We":[27,91],"demonstrate":[28],"how":[29],"vendor-specific":[30,74],"optimizations":[31],"can":[32,76],"invalidate":[33],"relative":[34],"performance":[35,41,56,102],"comparisons":[36],"architectural":[38],"archetypes,":[39],"with":[40],"advantages":[42],"sometimes":[43],"completely":[44],"reversing":[45],"after":[46],"compilation.":[47],"Our":[48,108],"systematic":[49],"analysis":[50],"reveals":[51],"that":[52,73],"exhibit":[55],"patterns":[57,79],"highly":[58],"dependent":[59],"on":[60],"both":[61],"architecture":[63],"batch":[65,105],"sizes.":[66],"Through":[67],"fine-grained":[68],"block-level":[69],"experimentation,":[70],"we":[71],"establish":[72],"leverage":[77],"repeated":[78],"in":[80],"simple":[81],"architectures,":[82],"yielding":[83],"disproportionate":[84],"throughput":[85],"gains":[86],"as":[87,104],"model":[88],"depth":[89],"increases.":[90,107],"introduce":[92],"novel":[93],"metrics":[94],"to":[95,100],"quantify":[96],"compiler's":[98],"ability":[99],"mitigate":[101],"friction":[103],"size":[106],"methodology":[109],"bridges":[110],"academic":[114],"research":[115,125],"by":[119],"incorporating":[120],"compiler":[121],"effects":[122],"throughout":[123],"process,":[126],"providing":[127],"actionable":[128],"insights":[129],"for":[130],"practitioners":[131],"navigating":[132],"complex":[133],"landscapes":[135],"environments.":[139]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
