{"id":"https://openalex.org/W4320060387","doi":"https://doi.org/10.1109/icdm54844.2022.00169","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","display_name":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","alternate_titles":[],"publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4320060387","doi":"https://doi.org/10.1109/icdm54844.2022.00169"},"language":"en","primary_location":{"id":"doi:10.1109/icdm54844.2022.00169","doi":"https://doi.org/10.1109/icdm54844.2022.00169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm54844.2022.00169","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4320060387"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.06462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100688739","display_name":"Yujun Yan","orcid":"https://orcid.org/0000-0003-3776-4293","observed_orcids":["https://orcid.org/0000-0003-3776-4293"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujun Yan","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026546407","display_name":"Milad Hashemi","orcid":"https://orcid.org/0009-0008-9345-607X","observed_orcids":["https://orcid.org/0009-0008-9345-607X"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milad Hashemi","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026208886","display_name":"Kevin Swersky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Swersky","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994183","display_name":"Yaoqing Lamar Yang","orcid":"https://orcid.org/0000-0001-9908-5531","observed_orcids":["https://orcid.org/0000-0001-9908-5531"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaoqing Yang","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015996266","display_name":"Danai Koutra","orcid":"https://orcid.org/0000-0002-3206-8179","observed_orcids":["https://orcid.org/0000-0002-3206-8179"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danai Koutra","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.8162,"has_fulltext":true,"cited_by_count":394,"citation_normalized_percentile":{"value":0.99697035,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1287","last_page":"1292"},"is_retracted":false,"is_pulled":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/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/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.9620000123977661},{"id":"https://openalex.org/keywords/over-smoothing","display_name":"over-smoothing","score":0.8550000190734863},{"id":"https://openalex.org/keywords/heterophily","display_name":"heterophily","score":0.9679999947547913},{"id":"https://openalex.org/keywords/node-classification","display_name":"node classification","score":0.9760000109672546},{"id":"https://openalex.org/keywords/edge-correction","display_name":"edge correction","score":0.5799999833106995},{"id":"https://openalex.org/keywords/relative-degree","display_name":"relative degree","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6055350303649902},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5935386419296265},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5033165812492371},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.48900306224823},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44501155614852905},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43249496817588806},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4209161698818207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38763532042503357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28519654273986816},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0721297562122345},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdm54844.2022.00169","doi":"https://doi.org/10.1109/icdm54844.2022.00169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm54844.2022.00169","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.06462","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06462","pdf_url":"https://arxiv.org/pdf/2102.06462","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.2102.06462","doi":"https://doi.org/10.48550/arxiv.2102.06462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06462","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.06462","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06462","pdf_url":"https://arxiv.org/pdf/2102.06462","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4320060387.pdf","grobid_xml":"https://content.openalex.org/works/W4320060387.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W67413104","https://openalex.org/W2040956707","https://openalex.org/W2107559689","https://openalex.org/W2148123869","https://openalex.org/W2153959628","https://openalex.org/W2162150749","https://openalex.org/W2468907370","https://openalex.org/W2519887557","https://openalex.org/W2606780347","https://openalex.org/W2624431344","https://openalex.org/W2765574772","https://openalex.org/W2766453196","https://openalex.org/W2770468159","https://openalex.org/W2787705367","https://openalex.org/W2804057010","https://openalex.org/W2894175828","https://openalex.org/W2900470550","https://openalex.org/W2916106175","https://openalex.org/W2949911880","https://openalex.org/W2952215816","https://openalex.org/W2964051675","https://openalex.org/W2964282455","https://openalex.org/W2965774812","https://openalex.org/W2975868979","https://openalex.org/W2975966238","https://openalex.org/W2978508283","https://openalex.org/W2981525344","https://openalex.org/W2990045899","https://openalex.org/W2995509042","https://openalex.org/W2995914187","https://openalex.org/W2996268457","https://openalex.org/W2998496395","https://openalex.org/W3030661718","https://openalex.org/W3034492151","https://openalex.org/W3035110173","https://openalex.org/W3090016979","https://openalex.org/W3090999459","https://openalex.org/W3093814892","https://openalex.org/W3101935724","https://openalex.org/W3122875465","https://openalex.org/W3128443161","https://openalex.org/W3132725505","https://openalex.org/W3168349256","https://openalex.org/W3200726313","https://openalex.org/W3208238874","https://openalex.org/W3209520664","https://openalex.org/W4224927254","https://openalex.org/W4287119647","https://openalex.org/W4288080007","https://openalex.org/W6748555532"],"related_works":["https://openalex.org/W4306920765","https://openalex.org/W3088367830","https://openalex.org/W4308164949","https://openalex.org/W3036490401","https://openalex.org/W4385740931","https://openalex.org/W4377000456","https://openalex.org/W7133227520","https://openalex.org/W3200726313","https://openalex.org/W3093814892"],"abstract_inverted_index":{"In":[0],"node":[1,103,119,143,199],"classification":[2],"tasks,":[3],"graph":[4,18,78],"convolutional":[5],"neural":[6],"networks":[7],"(GCNs)":[8],"have":[9,40],"demonstrated":[10],"competitive":[11],"performance":[12,26,157],"over":[13],"traditional":[14],"methods":[15],"on":[16,161,242],"diverse":[17],"data.":[19],"However,":[20],"it":[21],"is":[22],"known":[23],"that":[24,43,131,216],"the":[25,77,86,96,102,108,114,125,132,147,156,171,222],"of":[27,33,117,134,142,158,173,235],"GCNs":[28,44],"degrades":[29],"with":[30],"increasing":[31],"number":[32],"layers":[34],"(oversmoothing":[35],"problem)":[36],"and":[37,70,98,124,149,153,169,189,240],"recent":[38],"studies":[39],"also":[41],"shown":[42],"may":[45],"perform":[46],"worse":[47],"in":[48,227,238],"heterophilous":[49],"graphs,":[50],"where":[51],"neighboring":[52],"nodes":[53,109],"tend":[54,206],"to":[55,57,88,93,121,202,207],"belong":[56],"different":[58],"classes":[59],"(heterophily":[60],"problem).":[61],"These":[62],"two":[63,111,136,174,223],"problems":[64,100,151],"are":[65,72,85],"usually":[66],"viewed":[67],"as":[68],"unrelated,":[69],"thus":[71],"studied":[73],"independently,":[74],"often":[75],"at":[76,101],"filter":[79],"level":[80],"from":[81,163,184,198],"a":[82,90,118,232],"spectral":[83],"perspective.We":[84],"first":[87],"take":[89],"unified":[91],"perspective":[92],"jointly":[94,152],"explain":[95,146],"oversmoothing":[97,148],"heterophily":[99,150,211],"level.":[104],"Specifically,":[105],"we":[106,166,214],"profile":[107],"via":[110],"quantitative":[112],"metrics:":[113],"relative":[115],"degree":[116],"(compared":[120],"its":[122],"neighbors)":[123],"node-level":[126],"heterophily.":[127],"Our":[128],"theory":[129],"shows":[130],"interplay":[133],"these":[135],"profiling":[137],"metrics":[138],"defines":[139],"three":[140],"cases":[141],"behaviors,":[144],"which":[145,179,193,205,220],"can":[154],"predict":[155],"GCNs.":[159],"Based":[160],"insights":[162],"our":[164,217],"theory,":[165],"show":[167,215],"theoretically":[168],"empirically":[170],"effectiveness":[172],"strategies:":[175],"structure-based":[176],"edge":[177,182,191,196],"correction,":[178,192],"learns":[180,194],"corrected":[181],"weights":[183,197],"structural":[185],"properties":[186],"(i.e.,":[187],"degrees),":[188],"feature-based":[190],"signed":[195],"features.":[200],"Compared":[201],"other":[203],"approaches,":[204],"handle":[208],"well":[209,226],"either":[210],"or":[212],"oversmoothing,":[213],"model,":[218],"GGCN,":[219],"incorporates":[221],"strategies":[224],"performs":[225],"both":[228],"problems.":[229],"We":[230],"provide":[231],"longer":[233],"version":[234],"this":[236],"paper":[237],"[1]":[239],"codes":[241],"https://github.com/YujunYan/Heterophily_and_oversmoothing.":[243]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4320060387","counts_by_year":[{"year":2026,"cited_by_count":55},{"year":2025,"cited_by_count":94},{"year":2024,"cited_by_count":129},{"year":2023,"cited_by_count":60},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":17}],"updated_date":"2026-11-19T14:11:59.513116","created_date":"2023-02-12T00:00:00"}
