{"id":"https://openalex.org/W7163189597","doi":"https://doi.org/10.48550/arxiv.2606.00934","title":"Efficient Synthetic Network Generation via Latent Embedding Reconstruction","display_name":"Efficient Synthetic Network Generation via Latent Embedding Reconstruction","publication_year":2026,"publication_date":"2026-05-31","ids":{"openalex":"https://openalex.org/W7163189597","doi":"https://doi.org/10.48550/arxiv.2606.00934"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00934","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025221028","display_name":"Feifan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Feifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064018447","display_name":"Yinan Bu","orcid":"https://orcid.org/0009-0004-3021-7718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bu, Yinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137634308","display_name":"Shihao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137619056","display_name":"Gongjun Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Gongjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137652949","display_name":"Ji Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5931000113487244,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5931000113487244,"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":0.12999999523162842,"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/T12303","display_name":"Tensor decomposition and applications","score":0.03929999843239784,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6837999820709229},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5217000246047974},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4893999993801117},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4878999888896942},{"id":"https://openalex.org/keywords/network-simulation","display_name":"Network simulation","score":0.41040000319480896},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3912999927997589},{"id":"https://openalex.org/keywords/network-model","display_name":"Network model","score":0.37959998846054077},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7031000256538391},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6837999820709229},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4878999888896942},{"id":"https://openalex.org/C139940560","wikidata":"https://www.wikidata.org/wiki/Q290036","display_name":"Network simulation","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C68416499","wikidata":"https://www.wikidata.org/wiki/Q7001033","display_name":"Network formation","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00934","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00934","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Network":[0,78],"data":[1,16,38],"are":[2,61],"ubiquitous":[3],"across":[4],"the":[5,121,142,145,154,160,200,203,213],"social":[6],"sciences,":[7],"biology,":[8],"and":[9,44,64,87,118,148,173,205,231],"information":[10],"systems.":[11],"Generating":[12],"realistic":[13],"synthetic":[14,56,91,151,206],"network":[15,21,32,42,57,92,99,116,157,225,229],"has":[17],"broad":[18],"applications":[19],"from":[20,141],"simulation":[22],"to":[23,35],"scientific":[24],"discovery.":[25],"However,":[26],"many":[27,187],"existing":[28,188,236],"black-box":[29],"approaches":[30],"for":[31,55,90,179],"generation":[33,58,93],"tend":[34],"overfit":[36],"observed":[37,103],"while":[39,177],"overlooking":[40],"characteristic":[41],"structure,":[43],"incur":[45],"substantial":[46],"computational":[47,184],"overhead":[48],"at":[49,241],"scale.":[50],"These":[51],"practical":[52],"challenges":[53],"call":[54],"methods":[59],"that":[60,94,221],"both":[62],"efficient":[63,88,180],"capable":[65],"of":[66,70,215],"capturing":[67],"structural":[68],"properties":[69],"networks.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"introduce":[76],"Synthetic":[77],"Generation":[79],"via":[80,112],"Latent":[81],"Embedding":[82],"Reconstruction":[83],"(SyNGLER),":[84],"a":[85,113,126],"general":[86],"framework":[89],"builds":[95],"on":[96,199],"latent":[97,109,114,122,146,155,161],"space":[98,115,123,147,156,162],"models.":[100],"Given":[101],"an":[102],"network,":[104],"SyNGLER":[105,134,164],"first":[106,135],"learns":[107],"low-dimensional":[108],"node":[110,139,174],"embeddings":[111,140],"model":[117],"then":[119,149],"reconstructs":[120],"by":[124,195],"building":[125],"distribution-free":[127],"generator":[128,143],"over":[129],"these":[130],"embeddings.":[131],"For":[132],"generation,":[133],"samples":[136],"(or":[137],"resamples)":[138],"in":[144,168],"produces":[150,219],"networks":[152,169,220],"using":[153],"model.":[158],"Through":[159],"framework,":[163],"preserves":[165],"unique":[166],"characteristics":[167,226],"such":[170,227],"as":[171,228],"sparsity":[172],"degree":[175,232],"heterogeneity,":[176],"allowing":[178],"training":[181],"with":[182,235],"lower":[183],"cost":[185],"than":[186],"deep":[189],"architectures.":[190],"We":[191],"provide":[192],"theoretical":[193],"guarantees":[194],"developing":[196],"consistency":[197],"results":[198],"distance":[201],"between":[202],"true":[204],"edge":[207],"distributions.":[208],"Empirical":[209],"studies":[210],"further":[211],"demonstrate":[212],"effectiveness":[214],"SyNGLER,":[216],"which":[217],"efficiently":[218],"better":[222],"preserve":[223],"key":[224],"moments":[230],"distributions":[233],"compared":[234],"approaches.":[237],"Code":[238],"is":[239],"available":[240],"https://github.com/FeifanJiang/syngler.":[242]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}