{"id":"https://openalex.org/W3190547258","doi":"https://doi.org/10.1109/tpami.2021.3104733","title":"A Simple Spectral Failure Mode for Graph Convolutional Networks","display_name":"A Simple Spectral Failure Mode for Graph Convolutional Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3190547258","doi":"https://doi.org/10.1109/tpami.2021.3104733","mag":"3190547258","pmid":"https://pubmed.ncbi.nlm.nih.gov/34388090"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3104733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3104733","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5031834098","display_name":"Carey E. Priebe","orcid":"https://orcid.org/0000-0002-0139-7201"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carey E. Priebe","raw_affiliation_strings":["Department of Applied Mathematics and Statistics (AMS), Center for Imaging Science (CIS), and the Mathematical Institute for Data Science (MINDS), Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics (AMS), Center for Imaging Science (CIS), and the Mathematical Institute for Data Science (MINDS), Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017159636","display_name":"Cencheng Shen","orcid":"https://orcid.org/0000-0003-1030-1432"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cencheng Shen","raw_affiliation_strings":["Department of Applied Economics and Statistics, University of Delaware, Newark, DE, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Economics and Statistics, University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109717247","display_name":"Ningyuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ningyuan Huang","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100783478","display_name":"Tianyi Chen","orcid":"https://orcid.org/0000-0002-6207-1344"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Chen","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4197,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69431836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"44","issue":"11","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998000264167786,"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":0.9998000264167786,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.6640802621841431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5663954019546509},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.558571994304657},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5271206498146057},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.5244674682617188},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5160224437713623},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5010964870452881},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45384496450424194},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.44213446974754333},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43491125106811523},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4305494725704193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4146074056625366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3776094913482666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2878466248512268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640802621841431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663954019546509},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.558571994304657},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5271206498146057},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.5244674682617188},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5160224437713623},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5010964870452881},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45384496450424194},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.44213446974754333},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43491125106811523},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4305494725704193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4146074056625366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3776094913482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2878466248512268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3104733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3104733","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34388090","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34388090","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1453699960","display_name":null,"funder_award_id":"2113099","funder_id":"https://openalex.org/F4320337380","funder_display_name":"Division of Mathematical Sciences"},{"id":"https://openalex.org/G5803531241","display_name":null,"funder_award_id":"FA8750-17-2-0112","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8563503599","display_name":"HDR TRIPODS: Institute for the Foundations of Graph and Deep Learning","funder_award_id":"1934979","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1902027874","https://openalex.org/W1959608418","https://openalex.org/W1963954507","https://openalex.org/W1987349051","https://openalex.org/W2097880196","https://openalex.org/W2102907934","https://openalex.org/W2132914434","https://openalex.org/W2136504847","https://openalex.org/W2150120952","https://openalex.org/W2612872092","https://openalex.org/W2613782204","https://openalex.org/W2754251575","https://openalex.org/W2888391702","https://openalex.org/W2943959761","https://openalex.org/W2962756421","https://openalex.org/W2962810718","https://openalex.org/W2963791934","https://openalex.org/W2964015378","https://openalex.org/W2964051675","https://openalex.org/W2966291568","https://openalex.org/W3009381467","https://openalex.org/W3041063529","https://openalex.org/W3041085747","https://openalex.org/W3094049010","https://openalex.org/W3098465726","https://openalex.org/W3103168877","https://openalex.org/W3104477937","https://openalex.org/W3105423481","https://openalex.org/W4206482253","https://openalex.org/W4322614756","https://openalex.org/W6640963894","https://openalex.org/W6680140577","https://openalex.org/W6726873649","https://openalex.org/W6730084236","https://openalex.org/W6737474719","https://openalex.org/W6744139208","https://openalex.org/W6754929296","https://openalex.org/W6760001035","https://openalex.org/W6763152702","https://openalex.org/W6763216505","https://openalex.org/W6763392795","https://openalex.org/W6765465941","https://openalex.org/W6766750229","https://openalex.org/W6768314895","https://openalex.org/W6773400236","https://openalex.org/W6774263817","https://openalex.org/W6779367026"],"related_works":["https://openalex.org/W4213150077","https://openalex.org/W2369410163","https://openalex.org/W2059018062","https://openalex.org/W2604585036","https://openalex.org/W2078477160","https://openalex.org/W1989103179","https://openalex.org/W1991172810","https://openalex.org/W125803343","https://openalex.org/W2153421018","https://openalex.org/W2117632582"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"have":[2],"achieved":[3],"remarkable":[4],"successes":[5],"in":[6,27,81,90],"machine":[7],"learning":[8,17,40],"tasks.":[9],"This":[10],"has":[11],"recently":[12],"been":[13],"extended":[14],"to":[15,37,75],"graph":[16,58,70],"using":[18],"neural":[19],"networks.":[20],"However,":[21],"there":[22],"is":[23,73,95],"limited":[24],"theoretical":[25],"work":[26],"understanding":[28],"how":[29],"and":[30,100],"when":[31],"they":[32],"perform":[33],"well,":[34],"especially":[35],"relative":[36],"established":[38],"statistical":[39],"techniques":[41],"such":[42],"as":[43],"spectral":[44,65],"embedding.":[45],"In":[46],"this":[47],"short":[48],"paper,":[49],"we":[50],"present":[51],"a":[52],"simple":[53],"generative":[54],"model":[55],"where":[56],"unsupervised":[57,69],"convolutional":[59,71],"network":[60,72],"fails,":[61],"while":[62],"the":[63,78],"adjacency":[64],"embedding":[66],"succeeds.":[67],"Specifically,":[68],"unable":[74],"look":[76],"beyond":[77],"first":[79],"eigenvector":[80],"certain":[82],"approximately":[83],"regular":[84],"graphs,":[85],"thus":[86],"missing":[87],"inference":[88],"signals":[89],"non-leading":[91],"eigenvectors.":[92],"The":[93],"phenomenon":[94],"demonstrated":[96],"by":[97],"visual":[98],"illustrations":[99],"comprehensive":[101],"simulations.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}