{"id":"https://openalex.org/W2945625259","doi":null,"title":"Graph convolutional neural networks for the travelling salesman problem","display_name":"Graph convolutional neural networks for the travelling salesman problem","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2945625259","mag":"2945625259"},"language":"en","primary_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/77027","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10356/77027","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Final Year Project (FYP)"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041429006","display_name":"Chaitanya K. Joshi","orcid":"https://orcid.org/0000-0003-4722-1815","observed_orcids":["https://orcid.org/0000-0003-4722-1815"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joshi, Chaitanya Krishna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5041429006"],"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/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.5443999767303467,"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"}},"topics":[{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.5443999767303467,"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"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.26339998841285706,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.09920000284910202,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/traveling-salesman-problem","display_name":"traveling salesman problem","score":0.8619999885559082},{"id":"https://openalex.org/keywords/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.9900000095367432},{"id":"https://openalex.org/keywords/combinatorial-optimization","display_name":"combinatorial optimization","score":0.9390000104904175},{"id":"https://openalex.org/keywords/np-hard-problems","display_name":"NP-hard problems","score":0.7350000143051147},{"id":"https://openalex.org/keywords/learning-heuristics","display_name":"learning heuristics","score":0.6299999952316284},{"id":"https://openalex.org/keywords/beam-search","display_name":"beam search","score":0.8500000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6123608350753784},{"id":"https://openalex.org/C175859090","wikidata":"https://www.wikidata.org/wiki/Q322212","display_name":"Travelling salesman problem","level":2,"score":0.5778045654296875},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5497737526893616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49566853046417236},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4244998097419739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3711564540863037},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.33902233839035034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2913176417350769},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22587987780570984}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dr.ntu.edu.sg:10356/77027","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10356/77027","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Final Year Project (FYP)"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W149946109","https://openalex.org/W1546457065","https://openalex.org/W1652378708","https://openalex.org/W2015861736","https://openalex.org/W2017708378","https://openalex.org/W2029242918","https://openalex.org/W2044683982","https://openalex.org/W2051719061","https://openalex.org/W2055569927","https://openalex.org/W2058937865","https://openalex.org/W2064675550","https://openalex.org/W2074485628","https://openalex.org/W2098578926","https://openalex.org/W2106378689","https://openalex.org/W2110953678","https://openalex.org/W2112796928","https://openalex.org/W2117666205","https://openalex.org/W2119717200","https://openalex.org/W2157523980","https://openalex.org/W2158787690","https://openalex.org/W2159397589","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2299115575","https://openalex.org/W2525778437","https://openalex.org/W2618170429","https://openalex.org/W2912555327","https://openalex.org/W2919115771","https://openalex.org/W2949117887","https://openalex.org/W2962756421","https://openalex.org/W2962979969","https://openalex.org/W2963043672","https://openalex.org/W2964338167"],"related_works":["https://openalex.org/W2948433391","https://openalex.org/W4293107948","https://openalex.org/W4399453664","https://openalex.org/W4210271172","https://openalex.org/W4388627140","https://openalex.org/W2963382544","https://openalex.org/W2980930344","https://openalex.org/W3034214690","https://openalex.org/W3135302029","https://openalex.org/W2891230096"],"abstract_inverted_index":{"Combinatorial":[0],"optimization":[1],"problems,":[2,6],"also":[3],"called":[4],"NP-hard":[5,100],"are":[7,13,26,41],"practical":[8],"constraint":[9],"satisfaction":[10],"problems":[11,30],"that":[12,189],"impossible":[14],"to":[15,28,33,74,125,137,233,246,249],"solve":[16,29],"optimally":[17],"at":[18],"large":[19],"scales.":[20],"In":[21],"practice,":[22],"handcrafted":[23],"heuristic":[24],"algorithms":[25,40],"able":[27],"with":[31,57,135,240],"up":[32,56,136,248],"a":[34,89,127,176],"million":[35],"variables":[36],"and":[37,52,116,122,155,210],"constraints.":[38],"These":[39],"the":[42,97,105,112,169,202,229],"backbone":[43],"of":[44,67,151,162,172,205],"modern":[45],"industries":[46],"such":[47],"as":[48],"transportation,":[49],"supply":[50],"chain,":[51],"scheduling.":[53],"However,":[54,166],"coming":[55],"good":[58],"heuristics":[59,78],"requires":[60],"significant":[61],"specialized":[62],"knowledge.":[63],"A":[64],"recent":[65,103],"line":[66],"work":[68],"investigates":[69],"using":[70],"deep":[71,91,146],"neural":[72],"networks":[73],"directly":[75],"learn":[76],"these":[77],"from":[79,187],"problem":[80,101,160,221,251],"instances":[81,161],"instead.":[82],"\\n":[83,194],"\\nIn":[84],"this":[85],"paper,":[86],"we":[87],"introduce":[88],"novel":[90],"learning":[92,147,231],"approach":[93,141],"for":[94,208,219,228],"approximately":[95],"solving":[96],"most":[98],"famous":[99],"in":[102,149,179,201,244],"history,":[104],"Travelling":[106],"Salesman":[107],"Problem.":[108],"We":[109,226],"focus":[110,235],"on":[111,159,168,183,217],"2D":[113],"Euclidean":[114],"TSP":[115,129,209],"use":[117],"Graph":[118],"Convolutional":[119],"Neural":[120],"Networks":[121],"beam":[123],"search":[124],"predict":[126],"valid":[128],"tour":[130],"given":[131],"an":[132,198],"input":[133],"graph":[134,164,184],"100":[138],"nodes.":[139],"Our":[140],"outperforms":[142],"all":[143],"recently":[144],"proposed":[145],"techniques":[148],"terms":[150],"both":[152],"solution":[153],"quality":[154],"speed":[156],"when":[157,181],"evaluated":[158,182],"fixed":[163],"sizes.":[165,252],"experiments":[167],"generalization":[170,242],"capabilities":[171,243],"our":[173],"models":[174,190,239],"show":[175],"drastic":[177],"drop":[178],"performance":[180,218],"sizes":[185,222],"different":[186],"those":[188],"were":[191],"trained":[192],"on.":[193],"\\nOur":[195],"results":[196],"highlight":[197],"important":[199],"flaw":[200],"current":[203],"paradigm":[204],"learning-based":[206],"approaches":[207,215],"combinatorial":[211],"optimization:":[212],"comparing":[213],"among":[214],"based":[216],"discrete":[220],"completely":[223],"ignores":[224],"generalization.":[225],"advocate":[227],"machine":[230],"community":[232],"switch":[234],"towards":[236],"building":[237],"size-agnostic":[238],"strong":[241],"order":[245],"scale":[247],"realistic":[250]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}