{"id":"https://openalex.org/W2963639956","doi":"https://doi.org/10.1145/3292500.3330897","title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","display_name":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963639956","doi":"https://doi.org/10.1145/3292500.3330897","mag":"2963639956"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330897","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330897","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101454834","display_name":"Hongyang Gao","orcid":"https://orcid.org/0000-0002-9020-9080"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongyang Gao","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052278550","display_name":"Shuiwang Ji","orcid":"https://orcid.org/0000-0002-4205-4563"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuiwang Ji","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101454834"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":5.7806,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96796463,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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":1.0,"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":0.9915000200271606,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9707000255584717,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802629470825195},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5711381435394287},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5632871389389038},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.5480785369873047},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5349475145339966},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5022377967834473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4013039469718933},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3225724697113037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802629470825195},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5711381435394287},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5632871389389038},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.5480785369873047},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5349475145339966},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5022377967834473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4013039469718933},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3225724697113037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330897","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330897","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5700204612","display_name":null,"funder_award_id":"IIS-190","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6846874733","display_name":null,"funder_award_id":"IIS-1908166 and IIS-1908198","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7472016702","display_name":null,"funder_award_id":"IIS-1908166","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/W2963639956.pdf","grobid_xml":"https://content.openalex.org/works/W2963639956.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1514535095","https://openalex.org/W1533861849","https://openalex.org/W1576278180","https://openalex.org/W1850742715","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2092750499","https://openalex.org/W2095705004","https://openalex.org/W2099438806","https://openalex.org/W2153635508","https://openalex.org/W2153959628","https://openalex.org/W2154851992","https://openalex.org/W2184466087","https://openalex.org/W2315403234","https://openalex.org/W2402144811","https://openalex.org/W2406128552","https://openalex.org/W2464655605","https://openalex.org/W2468907370","https://openalex.org/W2519887557","https://openalex.org/W2624431344","https://openalex.org/W2626778328","https://openalex.org/W2758584285","https://openalex.org/W2766453196","https://openalex.org/W2776507577","https://openalex.org/W2788919350","https://openalex.org/W2809418595","https://openalex.org/W2811124557","https://openalex.org/W2885380450","https://openalex.org/W2887181327","https://openalex.org/W2890909908","https://openalex.org/W2895340641","https://openalex.org/W2922228302","https://openalex.org/W2950178297","https://openalex.org/W2953384591","https://openalex.org/W2963091558","https://openalex.org/W2963341956","https://openalex.org/W2963716836","https://openalex.org/W2964121744","https://openalex.org/W3104097132","https://openalex.org/W3105136071","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W4383602045","https://openalex.org/W2932872266","https://openalex.org/W4392094631","https://openalex.org/W4389995241","https://openalex.org/W4320149722","https://openalex.org/W3213655484"],"abstract_inverted_index":{"Attention":[0,19],"operators":[1,20,36,158],"have":[2],"been":[3,64],"widely":[4],"applied":[5],"in":[6,143,192],"various":[7],"fields,":[8],"including":[9],"computer":[10],"vision,":[11],"natural":[12],"language":[13],"processing,":[14],"and":[15,80,103,178],"network":[16],"embedding":[17,180],"learning.":[18],"on":[21,45,118,135,175],"graph":[22,34,77,82,179],"data":[23],"enables":[24],"learnable":[25],"weights":[26],"when":[27],"aggregating":[28],"information":[29],"from":[30],"neighboring":[31],"nodes.":[32,96,112],"However,":[33],"attention":[35,78,83,89,127],"(GAOs)":[37],"consume":[38],"excessive":[39],"computational":[40,105,119,144,193],"resources,":[41,120,194],"preventing":[42],"their":[43],"applications":[44],"large":[46,199],"graphs.":[47,200],"In":[48,70],"addition,":[49],"GAOs":[50],"belong":[51],"to":[52,66,93,98,110,140,189,198],"the":[53,87,116,123,133,136,156],"family":[54],"of":[55,59],"soft":[56],"attention,":[57,61],"instead":[58],"hard":[60,76,88],"which":[62],"has":[63],"shown":[65],"yield":[67],"better":[68,161,171],"performance.":[69,162],"this":[71],"work,":[72],"we":[73,121],"propose":[74,122],"novel":[75],"operator~(hGAO)":[79],"channel-wise":[81],"operator~(cGAO).":[84],"hGAO":[85,100,168],"uses":[86],"mechanism":[90],"by":[91,107],"attending":[92,109],"only":[94,108],"important":[95,111],"Compared":[97],"GAO,":[99],"improves":[101],"performance":[102,172],"saves":[104],"cost":[106],"To":[113],"further":[114],"reduce":[115],"requirements":[117],"cGAO":[124,131,187],"that":[125,150,167,185],"performs":[126],"operations":[128],"along":[129],"channels.":[130],"avoids":[132],"dependency":[134],"adjacency":[137],"matrix,":[138],"leading":[139],"dramatic":[141,190],"reductions":[142],"resource":[145],"requirements.":[146],"Experimental":[147],"results":[148,164],"demonstrate":[149],"our":[151,186],"proposed":[152],"deep":[153],"models":[154],"with":[155],"new":[157],"achieve":[159],"consistently":[160],"Comparison":[163],"also":[165],"indicates":[166],"achieves":[169],"significantly":[170],"than":[173],"GAO":[174],"both":[176],"node":[177],"tasks.":[181],"Efficiency":[182],"comparison":[183],"shows":[184],"leads":[188],"savings":[191],"making":[195],"them":[196],"applicable":[197]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}