{"id":"https://openalex.org/W3168068379","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443440","title":"A Dual Approach to Graph CNNs","display_name":"A Dual Approach to Graph CNNs","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3168068379","doi":"https://doi.org/10.1109/ieeeconf51394.2020.9443440","mag":"3168068379"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf51394.2020.9443440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"article","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/A5101708161","display_name":"J. Y. Shi","orcid":"https://orcid.org/0000-0003-1607-5018"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Shi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002480344","display_name":"Mark Cheung","orcid":"https://orcid.org/0000-0002-5909-8853"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Cheung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075414973","display_name":"Wendy Summer","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wendy Summer","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045861415","display_name":"Jos\u00e9 M. F. Moura","orcid":"https://orcid.org/0000-0002-9822-8294"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose M. F. Moura","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101708161"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7075521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"1467","last_page":"1471"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9907000064849854,"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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9559000134468079,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.7074041366577148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5794422626495361},{"id":"https://openalex.org/keywords/graph-energy","display_name":"Graph energy","score":0.5159276723861694},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4224371612071991},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.41263484954833984},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4056060016155243},{"id":"https://openalex.org/keywords/voltage-graph","display_name":"Voltage graph","score":0.35191071033477783},{"id":"https://openalex.org/keywords/line-graph","display_name":"Line graph","score":0.34007692337036133},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3332408666610718},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32470259070396423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.287095308303833}],"concepts":[{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.7074041366577148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5794422626495361},{"id":"https://openalex.org/C78913703","wikidata":"https://www.wikidata.org/wiki/Q5597087","display_name":"Graph energy","level":5,"score":0.5159276723861694},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4224371612071991},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.41263484954833984},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4056060016155243},{"id":"https://openalex.org/C22149727","wikidata":"https://www.wikidata.org/wiki/Q7940747","display_name":"Voltage graph","level":4,"score":0.35191071033477783},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.34007692337036133},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3332408666610718},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32470259070396423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.287095308303833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf51394.2020.9443440","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf51394.2020.9443440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1990488619","https://openalex.org/W1991252559","https://openalex.org/W2142498761","https://openalex.org/W2558748708","https://openalex.org/W2765323781","https://openalex.org/W2918342466","https://openalex.org/W2919603742","https://openalex.org/W2962711740","https://openalex.org/W2962810718","https://openalex.org/W2964015378","https://openalex.org/W2970493342","https://openalex.org/W2994824608","https://openalex.org/W3009381467","https://openalex.org/W3047391881","https://openalex.org/W3096934581","https://openalex.org/W4288347098","https://openalex.org/W4288419263","https://openalex.org/W6681029592","https://openalex.org/W6726873649","https://openalex.org/W6745316256","https://openalex.org/W6754929296","https://openalex.org/W6760045743","https://openalex.org/W6762453230","https://openalex.org/W6771291428","https://openalex.org/W6774263817"],"related_works":["https://openalex.org/W4372284312","https://openalex.org/W2608378520","https://openalex.org/W4319994858","https://openalex.org/W3034120174","https://openalex.org/W3120733914","https://openalex.org/W2105594148","https://openalex.org/W2563497088","https://openalex.org/W2497161677","https://openalex.org/W2800334336","https://openalex.org/W3177365930"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,35],"networks":[2,36,60],"(CNNs)":[3],"have":[4,85],"been":[5,86,116],"very":[6],"successful":[7],"with":[8],"learning":[9],"on":[10,26,30,51,54,90,193],"grid-based":[11],"data":[12,28,52],"such":[13,57],"as":[14,58,120],"time":[15],"series":[16],"and":[17,61,105,128,152,186,196],"images.":[18],"However,":[19,83],"traditional":[20],"CNNs":[21,69,159,175],"do":[22],"not":[23],"perform":[24,49],"well":[25,50],"irregular-structured":[27],"defined":[29,53],"a":[31,55,71,110,136],"graph.":[32],"Graph":[33],"convolutional":[34,40,81,96,155],"(graph":[37],"CNNs)":[38],"define":[39],"layers":[41],"using":[42,160],"graph":[43,56,68,75,91,107,158,174,181],"signal":[44],"processing":[45],"(GSP)":[46],"concepts.":[47],"They":[48],"citation":[59],"NYC":[62],"taxi":[63],"pickup":[64],"data.":[65],"Polynomial":[66],"filter":[67],"use":[70],"polynomial":[72],"of":[73,173,190],"the":[74,80,95,99,121,124,142,154,163,171,188],"adjacency":[76,129],"matrix":[77],"A":[78],"in":[79,118,162],"layer.":[82],"they":[84],"shown":[87],"to":[88,123,135,141,179],"fail":[89],"classification":[92],"problems":[93],"when":[94,177],"layer":[97,156],"produces":[98],"same":[100],"output":[101],"for":[102,157],"non-isomorphic":[103],"graphs":[104],"identical":[106],"signals.":[108],"Recently,":[109],"spectral":[111,137,164],"domain":[112,126,138,145],"shift,":[113],"M,":[114],"has":[115,133],"proposed":[117],"GSP":[119],"dual":[122,140],"vertex":[125,144],"shift":[127],"matrix,":[130],"A.":[131],"This":[132],"led":[134],"theory,":[139],"existing":[143],"theory.":[146],"In":[147,166],"this":[148],"paper,":[149],"we":[150,169],"redefine":[151],"dualize":[153],"M":[161],"domain.":[165],"doing":[167],"so,":[168],"solve":[170],"problem":[172],"failing":[176],"applied":[178],"certain":[180],"inputs.":[182],"We":[183],"show":[184],"theoretically":[185],"experimentally":[187],"advantages":[189],"our":[191],"solution":[192],"both":[194],"synthetic":[195],"real":[197],"datasets.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}