{"id":"https://openalex.org/W3209846642","doi":null,"title":"Tackling Oversmoothing of GNNs with Contrastive Learning.","display_name":"Tackling Oversmoothing of GNNs with Contrastive Learning.","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3209846642","mag":"3209846642"},"language":"en","primary_location":{"id":"mag:3209846642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.13798","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.13798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018530326","display_name":"Lecheng Zheng","orcid":"https://orcid.org/0000-0002-6869-3320","observed_orcids":["https://orcid.org/0000-0002-6869-3320"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lecheng Zheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6869-3320","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028848091","display_name":"Dongqi Fu","orcid":"https://orcid.org/0000-0002-8726-9234","observed_orcids":["https://orcid.org/0000-0002-8726-9234"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongqi Fu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8726-9234","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073158087","display_name":"Jingrui He","orcid":"https://orcid.org/0000-0002-6429-6272","observed_orcids":["https://orcid.org/0000-0002-6429-6272"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingrui He","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":"https://orcid.org/0000-0002-6429-6272","affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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/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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9229999780654907},{"id":"https://openalex.org/keywords/over-smoothing","display_name":"over-smoothing","score":0.9940000176429749},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8610000014305115},{"id":"https://openalex.org/keywords/node-classification","display_name":"node classification","score":0.746999979019165},{"id":"https://openalex.org/keywords/link-prediction","display_name":"link prediction","score":0.9679999947547913},{"id":"https://openalex.org/keywords/graph-representation-learning","display_name":"graph representation learning","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157372236251831},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5650542974472046},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5390163660049438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155851244926453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4517095983028412},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44294074177742004},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43251675367355347},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4121842086315155},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2897532880306244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13387733697891235},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09531986713409424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07459667325019836},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3209846642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.13798","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3209846642","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.13798","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2194775991","https://openalex.org/W2519887557","https://openalex.org/W2624431344","https://openalex.org/W2766453196","https://openalex.org/W2894175828","https://openalex.org/W2900763475","https://openalex.org/W2916106175","https://openalex.org/W2942483000","https://openalex.org/W2946439115","https://openalex.org/W2962767366","https://openalex.org/W2964051675","https://openalex.org/W2975868979","https://openalex.org/W2985331920","https://openalex.org/W2995914187","https://openalex.org/W2996268457","https://openalex.org/W2998496395","https://openalex.org/W3034492151","https://openalex.org/W3034693603","https://openalex.org/W3034978746","https://openalex.org/W3036446966","https://openalex.org/W3039465721","https://openalex.org/W3042770487","https://openalex.org/W3042786565","https://openalex.org/W3080902222","https://openalex.org/W3081102048","https://openalex.org/W3093766087","https://openalex.org/W3098957388","https://openalex.org/W3100345210","https://openalex.org/W3102419180","https://openalex.org/W3108655343","https://openalex.org/W4286748649","https://openalex.org/W4297808394","https://openalex.org/W4318185025"],"related_works":["https://openalex.org/W4379539177","https://openalex.org/W4312868626","https://openalex.org/W4390579897","https://openalex.org/W4353007232","https://openalex.org/W4413378426","https://openalex.org/W4221138897","https://openalex.org/W4312107640","https://openalex.org/W3013034147","https://openalex.org/W2998496395","https://openalex.org/W7103756646"],"abstract_inverted_index":{"Graph":[0,159],"neural":[1,17],"networks":[2],"(GNNs)":[3],"integrate":[4],"the":[5,12,23,48,51,66,71,87,100,109,117,130,157,166,176,182,186,189,202],"comprehensive":[6],"relation":[7],"of":[8,16,22,53,55,65,89,112,185,188,205],"graph":[9],"data":[10,68],"and":[11,29,41,82,120,134,151],"representation":[13],"learning":[14,27,178],"capability":[15],"networks,":[18],"which":[19,164],"is":[20,57,96,165],"one":[21],"most":[24],"popular":[25],"deep":[26],"methods":[28,133],"achieves":[30],"state-of-the-art":[31,209],"performance":[32,88,204],"in":[33],"many":[34],"applications,":[35],"such":[36],"as":[37],"natural":[38],"language":[39],"processing":[40],"computer":[42],"vision.":[43],"In":[44,105,124],"real-world":[45],"scenarios,":[46],"increasing":[47],"depth":[49],"(i.e.,":[50],"number":[52],"layers)":[54],"GNNs":[56],"sometimes":[58],"necessary":[59],"to":[60,69,139,200],"capture":[61],"more":[62,79,83],"latent":[63],"knowledge":[64],"input":[67],"mitigate":[70],"uncertainty":[72],"caused":[73],"by":[74],"missing":[75],"values.":[76],"However,":[77],"involving":[78],"complex":[80],"structures":[81],"parameters":[84],"will":[85],"decrease":[86],"GNN":[90],"models.":[91],"One":[92],"reason":[93],"called":[94],"oversmoothing":[95,107],"recently":[97],"introduced":[98],"but":[99,193],"relevant":[101],"research":[102],"remains":[103],"nascent.":[104],"general,":[106],"makes":[108],"final":[110],"representations":[111],"nodes":[113],"indiscriminative,":[114],"thus":[115],"deteriorating":[116],"node":[118],"classification":[119],"link":[121],"prediction":[122],"performance.":[123],"this":[125],"paper,":[126],"we":[127,155,180,196],"first":[128,167],"survey":[129],"current":[131],"de-oversmoothing":[132,142,168],"propose":[135,156],"three":[136,172],"major":[137],"metrics":[138],"evaluate":[140],"a":[141],"method,":[143],"i.e.,":[144],"constant":[145],"divergence":[146,149],"indicator,":[147,150],"easy-to-determine":[148],"model-agnostic":[152],"strategy.":[153],"Then,":[154],"Topology-guided":[158],"Contrastive":[160],"Layer,":[161],"named":[162],"TGCL,":[163],"method":[169],"maintaining":[170],"all":[171],"mentioned":[173],"metrics.":[174],"With":[175],"contrastive":[177],"manner,":[179],"provide":[181],"theoretical":[183],"analysis":[184],"effectiveness":[187],"proposed":[190],"TGCL.":[191],"Last":[192],"not":[194],"least,":[195],"design":[197],"extensive":[198],"experiments":[199],"illustrate":[201],"empirical":[203],"TGCL":[206],"comparing":[207],"with":[208],"baselines.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-11-08T00:00:00"}