{"id":"https://openalex.org/W7133358038","doi":"https://doi.org/10.48550/arxiv.2603.00430","title":"Efficient Decoder Scaling Strategy for Neural Routing Solvers","display_name":"Efficient Decoder Scaling Strategy for Neural Routing Solvers","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133358038","doi":"https://doi.org/10.48550/arxiv.2603.00430"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00430","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128030136","display_name":"Qing Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Qing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127993119","display_name":"Fu Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128003339","display_name":"Ke Li (106849)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128026186","display_name":"Zhenkun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhenkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.21050000190734863,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.21050000190734863,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1462000012397766,"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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.14339999854564667,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.8375999927520752},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5414000153541565},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.8375999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519000172615051},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5720000267028809},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00430","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00430","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4306708574295044,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Construction-based":[0],"neural":[1],"routing":[2,21],"solvers,":[3],"typically":[4],"composed":[5],"of":[6,50,80,130,163,170],"an":[7],"encoder":[8,32],"and":[9,92,106,127,135,158,172],"a":[10,15,60,78,85,161],"decoder,":[11],"have":[12],"emerged":[13],"as":[14],"promising":[16],"approach":[17],"for":[18,166],"solving":[19],"vehicle":[20],"problems.":[22],"While":[23],"recent":[24],"studies":[25],"suggest":[26],"that":[27,113,142],"shifting":[28],"parameters":[29,171],"from":[30,88],"the":[31,34,41,48,121,125,167,177],"to":[33,44,76,90,118,149,175],"decoder":[35,42],"enhances":[36],"performance,":[37,123],"most":[38],"works":[39],"restrict":[40],"size":[43],"1-3M":[45],"parameters,":[46],"leaving":[47],"effects":[49],"scaling":[51,67,70,96,143,150],"largely":[52],"unexplored.":[53],"To":[54],"address":[55],"this":[56],"gap,":[57],"we":[58,140,156],"conduct":[59],"systematic":[61],"study":[62],"comparing":[63],"two":[64],"distinct":[65,128],"strategies:":[66],"depth":[68,132,144],"versus":[69],"width.":[71,151],"We":[72],"synthesize":[73],"these":[74,154],"strategies":[75],"construct":[77],"suite":[79],"12":[81],"model":[82,122,131,178],"configurations,":[83],"spanning":[84],"parameter":[86,102,114],"range":[87],"1M":[89],"~150M,":[91],"extensively":[93],"evaluate":[94],"their":[95],"behaviors":[97],"across":[98],"three":[99],"critical":[100,126],"dimensions:":[101],"efficiency,":[103,105],"data":[104],"compute":[107,173],"efficiency.":[108],"Our":[109],"empirical":[110],"results":[111],"reveal":[112],"count":[115],"is":[116],"insufficient":[117],"accurately":[119],"predict":[120],"highlighting":[124],"roles":[129],"(layer":[133],"count)":[134],"width":[136],"(embedding":[137],"dimension).":[138],"Crucially,":[139],"demonstrate":[141],"yields":[145],"superior":[146],"performance":[147],"gains":[148],"Based":[152],"on":[153],"findings,":[155],"provide":[157],"experimentally":[159],"validate":[160],"set":[162],"design":[164],"principles":[165],"efficient":[168],"allocation":[169],"resources":[174],"enhance":[176],"performance.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}