{"id":"https://openalex.org/W3152560880","doi":"https://doi.org/10.1145/3442381.3449953","title":"Interpreting and Unifying Graph Neural Networks with An Optimization Framework","display_name":"Interpreting and Unifying Graph Neural Networks with An Optimization Framework","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3152560880","doi":"https://doi.org/10.1145/3442381.3449953","mag":"3152560880"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449953","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449953","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042775116","display_name":"Meiqi Zhu","orcid":"https://orcid.org/0000-0003-4753-0255"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meiqi Zhu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411469","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-4444-7811"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032218432","display_name":"Houye Ji","orcid":"https://orcid.org/0000-0002-1465-238X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houye Ji","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Cui","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042775116"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":13.9733,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.99118359,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1215","last_page":"1226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9825000166893005,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7523216009140015},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.547137975692749},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4973171055316925},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.45857033133506775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43773290514945984},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4362007677555084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3836607038974762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523216009140015},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.547137975692749},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4973171055316925},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.45857033133506775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43773290514945984},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4362007677555084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3836607038974762},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3449953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449953","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449953","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449953","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1497443639","https://openalex.org/W2095727900","https://openalex.org/W2468907370","https://openalex.org/W2784814091","https://openalex.org/W2899771611","https://openalex.org/W2907492528","https://openalex.org/W2907620438","https://openalex.org/W2911286998","https://openalex.org/W2914721378","https://openalex.org/W2918025264","https://openalex.org/W2949945331","https://openalex.org/W2962711740","https://openalex.org/W2962767366","https://openalex.org/W2962779575","https://openalex.org/W2963312446","https://openalex.org/W2964166731","https://openalex.org/W2964251001","https://openalex.org/W2964311892","https://openalex.org/W2964732194","https://openalex.org/W2965857891","https://openalex.org/W2972317931","https://openalex.org/W2982490267","https://openalex.org/W2994872359","https://openalex.org/W2995914187","https://openalex.org/W2995983896","https://openalex.org/W2996268457","https://openalex.org/W3011667710","https://openalex.org/W3012833893","https://openalex.org/W3034492151","https://openalex.org/W3034733365","https://openalex.org/W3036446966","https://openalex.org/W3039806961","https://openalex.org/W3042770487","https://openalex.org/W3080510905","https://openalex.org/W3081203761","https://openalex.org/W3099152386","https://openalex.org/W3099375322","https://openalex.org/W3208180646","https://openalex.org/W4210257598"],"related_works":["https://openalex.org/W2383807498","https://openalex.org/W1978572805","https://openalex.org/W1989941125","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W2149980199","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W4213275102","https://openalex.org/W4226363941"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,219],"received":[5],"considerable":[6],"attention":[7],"on":[8,129,202],"graph-structured":[9],"data":[10],"learning":[11],"for":[12,143,163,196,230],"a":[13,40,61,69,92,97,104,126],"wide":[14,98],"variety":[15],"of":[16,32,36,78,100,118],"tasks.":[17],"The":[18],"well-designed":[19],"propagation":[20,66,85],"mechanism":[21],"which":[22],"has":[23,46],"been":[24,47],"demonstrated":[25],"effective":[26],"is":[27],"the":[28,76,88,114,119,131,149,189,197,208,214,228],"most":[29,35,120],"fundamental":[30],"part":[31],"GNNs.":[33,147],"Although":[34],"GNNs":[37,210,232],"basically":[38],"follow":[39],"message":[41],"passing":[42],"manner,":[43],"litter":[44],"effort":[45],"made":[48],"to":[49,222],"discover":[50,153],"and":[51,167,192,225],"analyze":[52],"their":[53,83],"essential":[54],"relations.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,152,168,187],"establish":[60],"surprising":[62],"connection":[63],"between":[64,116,133],"different":[65,134],"mechanisms":[67,86],"with":[68,103,233],"unified":[70,110,235],"optimization":[71,111,236],"problem,":[72],"showing":[73,179],"that":[74,154,207],"despite":[75],"proliferation":[77],"various":[79],"GNNs,":[80,122,135],"in":[81],"fact,":[82],"proposed":[84,109,150,198,209],"are":[87],"optimal":[89],"solution":[90],"optimizing":[91],"feature":[93,164],"fitting":[94,165],"function":[95],"over":[96],"class":[99],"graph":[101,105,160,177],"kernels":[102,162,178],"regularization":[106],"term.":[107],"Our":[108],"framework,":[112,151],"summarizing":[113],"commonalities":[115],"several":[117],"representative":[121],"not":[123,211],"only":[124,212],"provides":[125],"macroscopic":[127],"view":[128],"surveying":[130],"relations":[132],"but":[136,217],"also":[137,218],"further":[138,169,226],"opens":[139],"up":[140],"new":[141,146],"opportunities":[142],"flexibly":[144],"designing":[145,231],"With":[148],"existing":[155],"works":[156],"usually":[157],"utilize":[158],"na\u00efve":[159],"convolutional":[161],"function,":[166],"develop":[170],"two":[171],"novel":[172],"objective":[173],"functions":[174],"considering":[175],"adjustable":[176],"low-pass":[180],"or":[181],"high-pass":[182],"filtering":[183],"capabilities":[184],"respectively.":[185],"Moreover,":[186],"provide":[188],"convergence":[190],"proofs":[191],"expressive":[193],"power":[194],"comparisons":[195],"models.":[199],"Extensive":[200],"experiments":[201],"benchmark":[203],"datasets":[204],"clearly":[205],"show":[206],"outperform":[213],"state-of-the-art":[215],"methods":[216],"good":[220],"ability":[221],"alleviate":[223],"over-smoothing,":[224],"verify":[227],"feasibility":[229],"our":[234],"framework.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":8}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}