{"id":"https://openalex.org/W3137729291","doi":"https://doi.org/10.48550/arxiv.2103.11414","title":"Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction","display_name":"Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction","publication_year":2021,"publication_date":"2021-03-21","ids":{"openalex":"https://openalex.org/W3137729291","doi":"https://doi.org/10.48550/arxiv.2103.11414","mag":"3137729291"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.11414","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.11414","pdf_url":"https://arxiv.org/pdf/2103.11414","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.11414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101974344","display_name":"Xinxing Wu","orcid":"https://orcid.org/0000-0001-9177-9352","observed_orcids":["https://orcid.org/0000-0001-9177-9352"]},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Xinxing","raw_affiliation_strings":["University of Kentucky , Lexington , Kentucky , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky , Lexington , Kentucky , U.S.A","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768220","display_name":"Qiang Shawn Cheng","orcid":"https://orcid.org/0000-0002-3596-2838","observed_orcids":["https://orcid.org/0000-0002-3596-2838","https://orcid.org/0000-0002-5329-8811","https://orcid.org/0000-0002-4370-2120"]},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng, Qiang","raw_affiliation_strings":["University of Kentucky , Lexington , Kentucky , U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky , Lexington , Kentucky , U.S.A","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/link-prediction","display_name":"link prediction","score":0.9229999780654907},{"id":"https://openalex.org/keywords/graph-autoencoder","display_name":"graph autoencoder","score":0.9940000176429749},{"id":"https://openalex.org/keywords/skip-connections","display_name":"skip connections","score":0.875},{"id":"https://openalex.org/keywords/low-dimensional-representation","display_name":"low-dimensional representation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/polynomial-filters","display_name":"polynomial filters","score":0.7409999966621399},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7829999923706055},{"id":"https://openalex.org/keywords/embedding-stability","display_name":"embedding stability","score":0.4300000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267679572105408},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6323868036270142},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6120404601097107},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.598730206489563},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.5479587912559509},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.539012610912323},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5217852592468262},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4963083863258362},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4960211217403412},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49086815118789673},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.46718552708625793},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.46266794204711914},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.4350919723510742},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.41673290729522705},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4149141311645508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39737626910209656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38241642713546753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33407944440841675},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27537328004837036},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2103.11414","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.11414","pdf_url":"https://arxiv.org/pdf/2103.11414","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,"listed_in":[],"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":"doi:10.48550/arxiv.2103.11414","doi":"https://doi.org/10.48550/arxiv.2103.11414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.11414","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,"listed_in":[],"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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.11414","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.11414","pdf_url":"https://arxiv.org/pdf/2103.11414","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3141641755","display_name":null,"funder_award_id":"W911NF-17","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1501856433","https://openalex.org/W1533861849","https://openalex.org/W1553673967","https://openalex.org/W1904365287","https://openalex.org/W2037933327","https://openalex.org/W2100495367","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2116341502","https://openalex.org/W2127048411","https://openalex.org/W2153959628","https://openalex.org/W2154851992","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2168627253","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2253807446","https://openalex.org/W2393319904","https://openalex.org/W2519887557","https://openalex.org/W2542024830","https://openalex.org/W2554952599","https://openalex.org/W2565538933","https://openalex.org/W2766453196","https://openalex.org/W2804057010","https://openalex.org/W2808409763","https://openalex.org/W2916106175","https://openalex.org/W2950697450","https://openalex.org/W2950789693","https://openalex.org/W2962937159","https://openalex.org/W2964051675","https://openalex.org/W2964121744","https://openalex.org/W2970843311","https://openalex.org/W2975966238","https://openalex.org/W2981525344","https://openalex.org/W2995509042","https://openalex.org/W2996268457","https://openalex.org/W3034492151"],"related_works":["https://openalex.org/W4285606307","https://openalex.org/W3158076488","https://openalex.org/W4300237897","https://openalex.org/W7160243082","https://openalex.org/W4241931197","https://openalex.org/W3100833928","https://openalex.org/W4212876221","https://openalex.org/W2899680271","https://openalex.org/W4401235054","https://openalex.org/W4416345211"],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2],"have":[3],"been":[4],"used":[5],"for":[6,59,134,160],"a":[7,26,54,130],"variety":[8],"of":[9,41,56,97,147,155],"learning":[10,30],"tasks,":[11],"such":[12],"as":[13],"link":[14,23,60,135,161],"prediction,":[15,61],"node":[16,19,116],"classification,":[17],"and":[18,68,71,83,115,150],"clustering.":[20],"Among":[21],"them,":[22],"prediction":[24],"is":[25],"relatively":[27],"under-studied":[28],"graph":[29,43,158],"task,":[31],"with":[32,175],"current":[33,57],"state-of-the-art":[34],"models":[35,159],"based":[36],"on":[37,52,140],"one-":[38],"or":[39],"two-layer":[40],"shallow":[42,66],"auto-encoder":[44],"(GAE)":[45],"architectures.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50,164],"focus":[51],"addressing":[53],"limitation":[55],"methods":[58,74,88,149],"which":[62],"can":[63],"only":[64],"use":[65],"GAEs":[67,119],"variational":[69],"GAEs,":[70,98],"creating":[72],"effective":[73],"to":[75,80,104,128],"deepen":[76],"(variational)":[77],"GAE":[78],"architectures":[79,96],"achieve":[81],"stable":[82],"competitive":[84,153],"performance.":[85],"Our":[86],"proposed":[87],"innovatively":[89],"incorporate":[90],"standard":[91,100],"auto-encoders":[92],"(AEs)":[93],"into":[94],"the":[95,112,145,152],"where":[99],"AEs":[101],"are":[102],"leveraged":[103],"learn":[105,129],"essential,":[106],"low-dimensional":[107,123],"representations":[108,124],"via":[109,125],"seamlessly":[110],"integrating":[111],"adjacency":[113],"information":[114],"features,":[117],"while":[118],"further":[120],"build":[121],"multi-scaled":[122],"residual":[126],"connections":[127],"compact":[131],"overall":[132],"embedding":[133],"prediction.":[136,162],"Empirically,":[137],"extensive":[138],"experiments":[139],"various":[141],"benchmarking":[142],"datasets":[143],"verify":[144],"effectiveness":[146],"our":[148,156,167],"demonstrate":[151],"performance":[154],"deepened":[157],"Theoretically,":[163],"prove":[165],"that":[166],"deep":[168],"extensions":[169],"inclusively":[170],"express":[171],"multiple":[172],"polynomial":[173],"filters":[174],"different":[176],"orders.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2021-03-29T00:00:00"}