{"id":"https://openalex.org/W4205669778","doi":"https://doi.org/10.1109/icdmw53433.2021.00093","title":"Graph Representation Learning with Adaptive Mixtures","display_name":"Graph Representation Learning with Adaptive Mixtures","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4205669778","doi":"https://doi.org/10.1109/icdmw53433.2021.00093"},"language":"en","primary_location":{"id":"doi:10.1109/icdmw53433.2021.00093","doi":"https://doi.org/10.1109/icdmw53433.2021.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw53433.2021.00093","pdf_url":null,"source":{"id":"https://openalex.org/S4393918563","display_name":"IEEE ... International Conference on Data Mining workshops","issn_l":"2375-9259","issn":["2375-9259"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4205669778"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5088081370","display_name":"Da Sun Handason Tam","orcid":"https://orcid.org/0000-0002-4961-7138","observed_orcids":["https://orcid.org/0000-0002-4961-7138"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Da Sun Handason Tam","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025216990","display_name":"Siyue Xie","orcid":"https://orcid.org/0000-0003-4362-6743","observed_orcids":["https://orcid.org/0000-0003-4362-6743"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyue Xie","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020413351","display_name":"Wing Cheong Lau","orcid":"https://orcid.org/0000-0003-1179-7855","observed_orcids":["https://orcid.org/0000-0003-1179-7855"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wing Cheong Lau","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"718"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.953000009059906},{"id":"https://openalex.org/keywords/node-representation-learning","display_name":"node representation learning","score":0.953000009059906},{"id":"https://openalex.org/keywords/mixture-models","display_name":"mixture models","score":0.6190000176429749},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.5860000252723694},{"id":"https://openalex.org/keywords/node-clustering","display_name":"node clustering","score":0.6890000104904175},{"id":"https://openalex.org/keywords/weight-sharing","display_name":"parameter sharing","score":0.5070000290870667},{"id":"https://openalex.org/keywords/translation-invariance","display_name":"translation invariance","score":0.8180000185966492},{"id":"https://openalex.org/keywords/node-classification","display_name":"node classification","score":0.7799999713897705},{"id":"https://openalex.org/keywords/joint-optimization","display_name":"joint optimization","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152907848358154},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5431084632873535},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5089449882507324},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4978749752044678},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44381722807884216},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4379030764102936},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43636026978492737},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4235371947288513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42133209109306335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32400351762771606},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw53433.2021.00093","doi":"https://doi.org/10.1109/icdmw53433.2021.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw53433.2021.00093","pdf_url":null,"source":{"id":"https://openalex.org/S4393918563","display_name":"IEEE ... International Conference on Data Mining workshops","issn_l":"2375-9259","issn":["2375-9259"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2519887557","https://openalex.org/W2604314403","https://openalex.org/W2624431344","https://openalex.org/W2756203131","https://openalex.org/W2766453196","https://openalex.org/W2768008502","https://openalex.org/W2769473888","https://openalex.org/W2792839479","https://openalex.org/W2804057010","https://openalex.org/W2811124557","https://openalex.org/W2894175828","https://openalex.org/W2914721378","https://openalex.org/W2918342466","https://openalex.org/W2945827377","https://openalex.org/W2946439115","https://openalex.org/W2946721323","https://openalex.org/W2961295589","https://openalex.org/W2970971581","https://openalex.org/W2997997679","https://openalex.org/W3021975806","https://openalex.org/W3028772300","https://openalex.org/W3034065136","https://openalex.org/W3038787377","https://openalex.org/W3103253084","https://openalex.org/W3116768744","https://openalex.org/W3138041058","https://openalex.org/W6780117690","https://openalex.org/W6792198074"],"related_works":["https://openalex.org/W4389492959","https://openalex.org/W3160144061","https://openalex.org/W6889049555","https://openalex.org/W7168124428","https://openalex.org/W4400910453","https://openalex.org/W3210188290","https://openalex.org/W4407569775","https://openalex.org/W4306317691","https://openalex.org/W7135170188","https://openalex.org/W4311138685"],"abstract_inverted_index":{"Graph":[0,78],"Neural":[1],"Networks":[2],"(GNNs)":[3],"are":[4,59],"the":[5,22,32,36,41,48,63,160,164,169,175,181,185,193,198,212,231,238],"current":[6],"state-of-the-art":[7,280],"models":[8,100,121,140,179,191],"in":[9,31,44,70,92,154,159,180,240,283],"learning":[10,89],"node":[11,90,130,207,255,284],"representations":[12,91],"for":[13,88,106,122,128,203,253,261],"many":[14,45],"predictive":[15],"tasks":[16],"on":[17,174,197,222,251,267],"graphs.":[18,72],"Typically,":[19],"GNNs":[20,53],"reuses":[21],"same":[23,232],"set":[24],"of":[25,137,168],"model":[26,239],"parameters":[27,195],"across":[28],"all":[29,138,189],"nodes":[30,57,228],"graph":[33,94,213],"to":[34,229,246,277],"improve":[35],"training":[37],"efficiency":[38],"and":[39,61,101,134,192],"exploit":[40,211],"translationally-invariant":[42],"properties":[43],"datasets.":[46],"However,":[47],"parameter":[49],"sharing":[50],"scheme":[51],"prevents":[52],"from":[54],"distinguishing":[55],"two":[56],"that":[58,62,114],"isomorphic":[60],"translation":[64],"invariance":[65],"property":[66],"may":[67],"not":[68],"exhibit":[69],"real-world":[71],"In":[73,184],"this":[74],"paper,":[75],"we":[76,145,162,187,216],"present":[77],"Representation":[79],"Learning":[80],"with":[81,132,150,271],"Adaptive":[82],"Mixtures":[83],"(GRAM),":[84],"a":[85,93,102,111,155,219],"novel":[86],"approach":[87],"by":[95],"introducing":[96],"multiple":[97],"independent":[98,177],"GNN":[99,139,178,190,281],"trainable":[103],"mixture":[104,194,233],"distribution":[105,167],"each":[107,262],"node.":[108,263],"GRAM":[109,244,266,274],"is":[110,275],"general":[112],"framework":[113],"can":[115],"be":[116],"readily":[117],"embedded":[118],"into":[119],"existing":[120],"enhancing":[123],"representation":[124,260],"learning.":[125],"It":[126],"allows":[127],"adaptive":[129],"clustering":[131],"mixtures":[133],"joint":[135],"optimization":[136],"simultaneously.":[141],"To":[142,209],"achieve":[143],"this,":[144],"develop":[146],"an":[147,241],"Expectation-Maximization":[148],"algorithm":[149],"stochastic":[151],"gradient":[152],"descent":[153],"scalable":[156],"manner.":[157],"Specifically,":[158],"E-Step,":[161],"approximate":[163],"posterior":[165],"probability":[166],"latent":[170,200],"cluster":[171,201],"membership":[172,202],"based":[173,196],"k-th":[176],"last":[182],"iteration.":[183],"M-step,":[186],"update":[188],"refined":[199],"downstream":[204],"tasks,":[205],"e.g.,":[206],"classification.":[208],"fully":[210],"structural":[214],"information,":[215],"further":[217],"implement":[218],"regularization":[220],"term":[221],"unlabeled":[223],"nodes,":[224],"which":[225,257],"encourages":[226],"adjacent":[227],"have":[230],"distribution.":[234],"By":[235],"jointly":[236],"optimizing":[237],"end-to-end":[242],"manner,":[243],"learns":[245],"capture":[247],"different":[248,254],"abstract":[249],"patterns":[250],"graphs":[252],"clusters,":[256],"yields":[258],"discriminative":[259],"We":[264],"evaluate":[265],"five":[268],"benchmark":[269],"datasets":[270],"extensive":[272],"experiments.":[273],"demonstrated":[276],"consistently":[278],"boost":[279],"variants":[282],"classification":[285],"tasks.":[286]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2022-01-25T00:00:00"}