{"id":"https://openalex.org/W3166257724","doi":"https://doi.org/10.1145/3447548.3467373","title":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","display_name":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3166257724","doi":"https://doi.org/10.1145/3447548.3467373","mag":"3166257724"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467373","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Susheel Suresh","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susheel Suresh","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Vinith Budde","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinith Budde","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jennifer Neville","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Neville","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jianzhu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianzhu Ma","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3251,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97887774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1541","last_page":"1551"},"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":0.9955999851226807,"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":0.9836999773979187,"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/assortativity","display_name":"Assortativity","score":0.9344000220298767},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5270000100135803},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46000000834465027},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4066999852657318},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40290001034736633},{"id":"https://openalex.org/keywords/graph-property","display_name":"Graph property","score":0.35179999470710754},{"id":"https://openalex.org/keywords/mixing-patterns","display_name":"Mixing patterns","score":0.3441999852657318},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.3345000147819519},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.3271999955177307}],"concepts":[{"id":"https://openalex.org/C89694873","wikidata":"https://www.wikidata.org/wiki/Q4810299","display_name":"Assortativity","level":3,"score":0.9344000220298767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5735999941825867},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5482000112533569},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.35179999470710754},{"id":"https://openalex.org/C65375091","wikidata":"https://www.wikidata.org/wiki/Q6884079","display_name":"Mixing patterns","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33160001039505005},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C7948225","wikidata":"https://www.wikidata.org/wiki/Q4723998","display_name":"Algebraic connectivity","level":4,"score":0.2808000147342682},{"id":"https://openalex.org/C157406716","wikidata":"https://www.wikidata.org/wiki/Q4115842","display_name":"Topological graph theory","level":5,"score":0.2736000120639801},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C32946077","wikidata":"https://www.wikidata.org/wiki/Q618079","display_name":"Network analysis","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3447548.3467373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467373","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.06586","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.06586","pdf_url":"https://arxiv.org/pdf/2106.06586","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,"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"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467373","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 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1298418195","display_name":null,"funder_award_id":"IIS-1618690","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1513559549","display_name":null,"funder_award_id":"CCF0-939370","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1623528200","display_name":null,"funder_award_id":"CCF-1918483,IIS-1618690,CCF-0939370","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1952775380","display_name":null,"funder_award_id":"CCF-1918483","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6244900323","display_name":"Emerging Frontiers of Science of Information","funder_award_id":"0939370","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G787217599","display_name":"FMitF: Track I: Symbolic Reasoning with Graph Networks","funder_award_id":"1918483","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8559347097","display_name":"III: Small: Transfer Learning Within and Across Networks for Collective Classification","funder_award_id":"1618690","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166257724.pdf","grobid_xml":"https://content.openalex.org/works/W3166257724.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2044744030","https://openalex.org/W2107559689","https://openalex.org/W2144994235","https://openalex.org/W2515786142","https://openalex.org/W2604314403","https://openalex.org/W2792234394","https://openalex.org/W2807021761","https://openalex.org/W2963316155","https://openalex.org/W3087257704","https://openalex.org/W3101444938"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"neural":[1],"networks":[2,67],"(GNNs)":[3],"have":[4],"achieved":[5],"tremendous":[6],"success":[7],"on":[8,154,201,236],"multiple":[9],"graph-based":[10],"learning":[11,243],"tasks":[12],"by":[13,31,44],"fusing":[14],"network":[15],"structure":[16,211],"and":[17,74,117,167,205,212],"node":[18,109,142,233],"features.":[19],"Modern":[20],"GNN":[21,135],"models":[22,136],"are":[23],"built":[24],"upon":[25],"iterative":[26],"aggregation":[27],"of":[28,79,122,130,134,173,183,226,239],"neighbor's/proximity":[29],"features":[30],"message":[32],"passing.":[33],"Its":[34],"prediction":[35,128],"performance":[36,129,217],"has":[37,179],"been":[38],"shown":[39],"to":[40,111,198,215],"be":[41,88],"strongly":[42],"bounded":[43],"assortative":[45],"mixing":[46,72],"in":[47,92,149],"the":[48,75,108,114,120,127,141,156,192,224],"graph,":[49],"a":[50,89,98,131,160,237],"key":[51],"property":[52],"wherein":[53],"nodes":[54],"with":[55,59,140],"similar":[56],"attributes":[57],"mix/connect":[58],"each":[60],"other.":[61],"We":[62,96,124,195],"observe":[63],"that":[64,104,126,207],"real":[65,240],"world":[66,241],"exhibit":[68],"heterogeneous":[69],"or":[70],"diverse":[71,115,219],"patterns":[73,116],"conventional":[76],"global":[77,83],"measurement":[78],"assortativity,":[80,102],"such":[81],"as":[82,170],"assortativity":[84,184],"coefficient,":[85],"may":[86],"not":[87],"representative":[90],"statistic":[91],"quantifying":[93],"this":[94,147,150,202],"mixing.":[95,220],"adopt":[97],"generalized":[99],"concept,":[100],"node-level":[101],"one":[103],"is":[105,137],"based":[106],"at":[107],"level":[110,143,182],"better":[112],"represent":[113],"accurately":[118],"quantify":[119],"learnability":[121],"GNNs.":[123],"find":[125],"wide":[132],"range":[133],"highly":[138],"correlated":[139],"assortativity.":[144],"To":[145],"break":[146],"limit,":[148],"work,":[151],"we":[152,222],"focus":[153],"transforming":[155],"input":[157],"graph":[158,162,178,204,242],"into":[159],"computation":[161,203],"which":[163],"contains":[164],"both":[165],"proximity":[166,213],"structural":[168],"information":[169,190],"distinct":[171],"type":[172],"edges.":[174],"The":[175],"resulted":[176],"multi-relational":[177],"an":[180],"enhanced":[181],"and,":[185],"more":[186],"importantly,":[187],"preserves":[188],"rich":[189],"from":[191],"original":[193],"graph.":[194],"then":[196],"propose":[197],"run":[199],"GNNs":[200],"show":[206,223],"adaptively":[208],"choosing":[209],"between":[210],"leads":[214],"improved":[216],"under":[218],"Empirically,":[221],"benefits":[225],"adopting":[227],"our":[228],"transformation":[229],"framework":[230],"for":[231],"semi-supervised":[232],"classification":[234],"task":[235],"variety":[238],"benchmarks.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":6}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2021-06-22T00:00:00"}