{"id":"https://openalex.org/W4401863994","doi":"https://doi.org/10.1145/3637528.3671731","title":"An Efficient Subgraph GNN with Provable Substructure Counting Power","display_name":"An Efficient Subgraph GNN with Provable Substructure Counting Power","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863994","doi":"https://doi.org/10.1145/3637528.3671731"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5047456533","display_name":"Zuoyu Yan","orcid":"https://orcid.org/0000-0003-2585-3838"},"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":true,"raw_author_name":"Zuoyu Yan","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junru Zhou","orcid":"https://orcid.org/0000-0002-1192-7712"},"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junru Zhou","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003588774","display_name":"L. Gao","orcid":"https://orcid.org/0000-0002-5196-4825"},"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":"Liangcai Gao","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"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":"Zhi Tang","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028722073","display_name":"Muhan Zhang","orcid":"https://orcid.org/0000-0002-7680-6401"},"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"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhan Zhang","raw_affiliation_strings":["Beijing Institute for General Artificial Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute for General Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047456533"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.009,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8026789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3702","last_page":"3713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983999729156494,"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":0.9983999729156494,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/substructure","display_name":"Substructure","score":0.876533031463623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6090782880783081},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06540808081626892}],"concepts":[{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.876533031463623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6090782880783081},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06540808081626892},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671731","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1553308638","https://openalex.org/W2126969584","https://openalex.org/W2560674852","https://openalex.org/W2605912794","https://openalex.org/W2907492528","https://openalex.org/W2962810718","https://openalex.org/W2962890986","https://openalex.org/W2965757697","https://openalex.org/W3016124664","https://openalex.org/W3035664258","https://openalex.org/W3041877813","https://openalex.org/W3042133669","https://openalex.org/W3081214609","https://openalex.org/W3092867907","https://openalex.org/W3094003325","https://openalex.org/W3126138172","https://openalex.org/W3152893301","https://openalex.org/W3163256474","https://openalex.org/W3169575312","https://openalex.org/W3171913066","https://openalex.org/W3187220393","https://openalex.org/W3208638341","https://openalex.org/W3209378310","https://openalex.org/W3210188290","https://openalex.org/W3211394146","https://openalex.org/W4225773884","https://openalex.org/W4281706128","https://openalex.org/W4286793199","https://openalex.org/W4286913454","https://openalex.org/W4287123803","https://openalex.org/W4297817821","https://openalex.org/W4327880158","https://openalex.org/W4385562565","https://openalex.org/W4385567890","https://openalex.org/W4385567983","https://openalex.org/W4385568239","https://openalex.org/W4385568381","https://openalex.org/W6775947557","https://openalex.org/W6798426842","https://openalex.org/W6802258442","https://openalex.org/W6802298853","https://openalex.org/W6803400136"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3153444835","https://openalex.org/W2153916713","https://openalex.org/W2023846184","https://openalex.org/W2703419385","https://openalex.org/W2329056228","https://openalex.org/W2284584236","https://openalex.org/W1979083399","https://openalex.org/W2344320748"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,21,41,90,101,109,136],"enhancement":[3],"of":[4,23,104,139],"graph":[5,30],"neural":[6],"networks'":[7],"(GNNs)":[8],"representation":[9],"power":[10,103,138],"through":[11],"their":[12,46],"ability":[13,47],"in":[14,95],"substructure":[15],"counting.":[16],"Recent":[17],"advances":[18],"have":[19],"seen":[20],"adoption":[22],"subgraph":[24,52,105,140],"GNNs,":[25],"which":[26],"partition":[27],"an":[28],"input":[29],"into":[31],"numerous":[32],"subgraphs,":[33,117],"subsequently":[34],"applying":[35,113],"GNNs":[36,53,74,141],"to":[37,39,48,75,92,99],"each":[38],"augment":[40],"graph's":[42],"overall":[43],"representation.":[44],"Despite":[45],"identify":[49],"various":[50],"substructures,":[51],"are":[54],"hindered":[55],"by":[56],"significant":[57],"computational":[58],"and":[59,80],"memory":[60],"costs.":[61],"In":[62],"this":[63,125],"paper,":[64],"we":[65,118],"tackle":[66],"a":[67,86],"critical":[68],"question:":[69],"Is":[70],"it":[71],"possible":[72],"for":[73,111],"count":[76],"substructures":[77],"both":[78],"efficiently":[79],"provably?":[81],"Our":[82],"approach":[83],"begins":[84],"with":[85],"theoretical":[87],"demonstration":[88],"that":[89,123,131],"distance":[91,127],"rooted":[93],"nodes":[94],"subgraphs":[96],"is":[97],"key":[98],"boosting":[100],"counting":[102,137],"GNNs.":[106],"To":[107],"avoid":[108],"need":[110],"repetitively":[112],"GNN":[114],"across":[115],"all":[116],"introduce":[119],"precomputed":[120],"structural":[121],"embeddings":[122],"encapsulate":[124],"crucial":[126],"information.":[128],"Experiments":[129],"validate":[130],"our":[132],"proposed":[133],"model":[134],"retains":[135],"while":[142],"achieving":[143],"significantly":[144],"faster":[145],"performance.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}