{"id":"https://openalex.org/W4372267823","doi":"https://doi.org/10.1109/icassp49357.2023.10095900","title":"Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks","display_name":"Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267823","doi":"https://doi.org/10.1109/icassp49357.2023.10095900"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095900","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5102003121","display_name":"Jin Zeng","orcid":"https://orcid.org/0000-0002-0180-7733"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zeng","raw_affiliation_strings":["Tongji University,Shanghai,China","Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Peking University,Beijing,China","Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038897476","display_name":"Gene Cheung","orcid":"https://orcid.org/0000-0002-5571-4137"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gene Cheung","raw_affiliation_strings":["York University,Toronto,Canada","York University, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University,Toronto,Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077498823","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0002-4809-7601"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Peking University,Beijing,China","Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73081303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9789000153541565,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/laplacian-matrix","display_name":"Laplacian matrix","score":0.6549460291862488},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6047652959823608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5895615220069885},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.4936431646347046},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4905168414115906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4781970977783203},{"id":"https://openalex.org/keywords/matrix-completion","display_name":"Matrix completion","score":0.47353455424308777},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4612286388874054},{"id":"https://openalex.org/keywords/graph-bandwidth","display_name":"Graph bandwidth","score":0.44568315148353577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520314395427704},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3219904899597168},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.24970605969429016},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.2170403003692627},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.08506748080253601}],"concepts":[{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.6549460291862488},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6047652959823608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5895615220069885},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.4936431646347046},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4905168414115906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4781970977783203},{"id":"https://openalex.org/C2778459887","wikidata":"https://www.wikidata.org/wiki/Q6787865","display_name":"Matrix completion","level":3,"score":0.47353455424308777},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4612286388874054},{"id":"https://openalex.org/C134727501","wikidata":"https://www.wikidata.org/wiki/Q5597073","display_name":"Graph bandwidth","level":5,"score":0.44568315148353577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520314395427704},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3219904899597168},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.24970605969429016},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.2170403003692627},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.08506748080253601},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095900","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W143236119","https://openalex.org/W1487444668","https://openalex.org/W1522301498","https://openalex.org/W1555827348","https://openalex.org/W1838651752","https://openalex.org/W1980811840","https://openalex.org/W2000769684","https://openalex.org/W2132555912","https://openalex.org/W2571662414","https://openalex.org/W2615556757","https://openalex.org/W2739744923","https://openalex.org/W2804057010","https://openalex.org/W2916106175","https://openalex.org/W2963358464","https://openalex.org/W2964015378","https://openalex.org/W2964051675","https://openalex.org/W2966445777","https://openalex.org/W2978508283","https://openalex.org/W2990045899","https://openalex.org/W2996268457","https://openalex.org/W3005644236","https://openalex.org/W3015741275","https://openalex.org/W3034492151","https://openalex.org/W3161082783","https://openalex.org/W4230938240","https://openalex.org/W6631190155","https://openalex.org/W6726873649","https://openalex.org/W6746015598","https://openalex.org/W6752110883","https://openalex.org/W6760001035","https://openalex.org/W6768314895","https://openalex.org/W6771621015","https://openalex.org/W6771932116","https://openalex.org/W6779961489"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2942366970","https://openalex.org/W2950359809","https://openalex.org/W2791118824","https://openalex.org/W2633605431","https://openalex.org/W3041034658","https://openalex.org/W3184441089"],"abstract_inverted_index":{"A":[0],"graph":[1,7,43,60,71,100,116,152],"convolutional":[2],"network":[3],"(GCN)":[4],"employs":[5],"a":[6,58,64,70,86,95,114],"filtering":[8],"kernel":[9],"tailored":[10],"for":[11,98,163,179],"data":[12,147],"with":[13,119,141],"irregular":[14],"structures.":[15],"However,":[16],"simply":[17],"stacking":[18],"more":[19],"GCN":[20,91,165],"layers":[21],"does":[22],"not":[23],"improve":[24],"performance;":[25],"instead,":[26],"the":[27,36,42,47,99,106,120,133,138,142,150],"output":[28,158],"converges":[29],"to":[30,68,104,185],"an":[31],"uninformative":[32],"low-dimensional":[33],"subspace,":[34],"where":[35],"convergence":[37],"rate":[38],"is":[39,46,160],"characterized":[40],"by":[41],"spectrum\u2014":[44],"this":[45,54],"known":[48],"over-smoothing":[49,75],"problem":[50,118],"in":[51,81],"GCN.":[52],"In":[53],"paper,":[55],"we":[56,93,112,131],"propose":[57],"sparse":[59,115],"learning":[61,117],"algorithm":[62],"incorporating":[63],"new":[65],"spectrum":[66,96,121,143,155],"prior":[67,97],"compute":[69],"topology":[72],"that":[73,169],"circumvents":[74],"while":[76],"preserving":[77],"pairwise":[78],"correlations":[79],"inherent":[80],"data.":[82],"Specifically,":[83],"based":[84,145],"on":[85,146,149],"spectral":[87],"analysis":[88],"of":[89],"multilayer":[90],"output,":[92],"derive":[94],"Laplacian":[101],"matrix":[102],"L":[103,159],"robustify":[105],"model":[107],"expressiveness":[108],"against":[109],"over-smoothing.":[110],"Then,":[111],"formulate":[113],"prior,":[122,144],"solved":[123],"efficiently":[124],"via":[125],"block":[126],"coordinate":[127],"descent":[128],"(BCD).":[129],"Moreover,":[130],"optimize":[132],"weight":[134],"parameter":[135],"trading":[136],"off":[137],"fidelity":[139],"term":[140],"smoothness":[148],"original":[151],"learned":[153],"without":[154],"manipulation.":[156],"The":[157],"then":[161],"normalized":[162],"supervised":[164],"training.":[166],"Experiments":[167],"show":[168],"our":[170],"proposal":[171],"produced":[172],"deeper":[173],"GCNs":[174],"and":[175,181],"higher":[176],"prediction":[177],"accuracy":[178],"regression":[180],"classification":[182],"tasks":[183],"compared":[184],"competing":[186],"schemes.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}