{"id":"https://openalex.org/W4396758716","doi":"https://doi.org/10.1145/3589334.3645586","title":"A Quasi-Wasserstein Loss for Learning Graph Neural Networks","display_name":"A Quasi-Wasserstein Loss for Learning Graph Neural Networks","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396758716","doi":"https://doi.org/10.1145/3589334.3645586"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3645586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","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/A5025741085","display_name":"Minjie Cheng","orcid":"https://orcid.org/0000-0003-1344-5749"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minjie Cheng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1344-5749","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"https://orcid.org/0000-0003-4192-5360"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongteng Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4192-5360","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025741085"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62070628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"815","last_page":"826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9922000169754028,"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":0.9768999814987183,"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/computer-science","display_name":"Computer science","score":0.7058206796646118},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5039946436882019},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4519389569759369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40532276034355164},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3312716484069824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058206796646118},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5039946436882019},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4519389569759369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40532276034355164},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3312716484069824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3645586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G128774786","display_name":null,"funder_award_id":"92270110","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1990334093","https://openalex.org/W2027731328","https://openalex.org/W2036996178","https://openalex.org/W2342070830","https://openalex.org/W2788284887","https://openalex.org/W2793477525","https://openalex.org/W2809583854","https://openalex.org/W2911286998","https://openalex.org/W2912083425","https://openalex.org/W2912269676","https://openalex.org/W2912636151","https://openalex.org/W2914721378","https://openalex.org/W2915480215","https://openalex.org/W2962792820","https://openalex.org/W2966859223","https://openalex.org/W2996858319","https://openalex.org/W3004507689","https://openalex.org/W3012562343","https://openalex.org/W3103513278","https://openalex.org/W3103596128","https://openalex.org/W3116202926","https://openalex.org/W3152560880","https://openalex.org/W3156441686","https://openalex.org/W3160872503","https://openalex.org/W3174022889","https://openalex.org/W3175662620","https://openalex.org/W3175753490","https://openalex.org/W3210034512","https://openalex.org/W3217672792","https://openalex.org/W4213437519","https://openalex.org/W4214868967","https://openalex.org/W4221144581","https://openalex.org/W4225982766","https://openalex.org/W4287115771","https://openalex.org/W4367046596","https://openalex.org/W4367046726","https://openalex.org/W6601955380","https://openalex.org/W6624914812","https://openalex.org/W6774341405"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"When":[0,144],"learning":[1,61,136],"graph":[2,32,89,107],"neural":[3],"networks":[4],"(GNNs)":[5],"in":[6,38,98,190],"node-level":[7,191],"prediction":[8,63,171],"tasks,":[9],"most":[10],"existing":[11],"loss":[12,47,130,179],"functions":[13],"are":[14,27,93],"applied":[15],"for":[16],"each":[17],"node":[18,22,78,146],"independently,":[19],"even":[20],"if":[21],"embeddings":[23],"and":[24,62,80,184,193],"their":[25,31,81,188],"labels":[26,79],"non-i.i.d.":[28],"because":[29],"of":[30,51,65,116,153,198],"structures.":[33],"To":[34],"eliminate":[35],"such":[36],"inconsistency,":[37],"this":[39,199],"study":[40],"we":[41,69,125],"propose":[42],"a":[43,71,96,121,168],"novel":[44],"Quasi-Wasserstein":[45,129],"(QW)":[46],"with":[48,132,140,156],"the":[49,52,75,84,100,106,113,117,127,137,151,154,157,162,176],"help":[50],"optimal":[53,101,141,163],"transport":[54,86,103,119],"defined":[55,87],"on":[56,88],"graphs,":[57],"leading":[58,166],"to":[59,120,167,181,186],"new":[60,169],"paradigms":[64],"GNNs.":[66],"In":[67],"particular,":[68],"design":[70],"\"Quasi-Wasserstein''":[72],"distance":[73],"between":[74],"observed":[76],"multi-dimensional":[77],"estimations,":[82],"optimizing":[83],"label":[85,102,118,142,164],"edges.":[90],"The":[91,196],"estimations":[92],"parameterized":[94],"by":[95,161],"GNN":[97,138,155],"which":[99],"may":[104],"determine":[105],"edge":[108],"weights":[109],"optionally.":[110],"By":[111],"reformulating":[112],"strict":[114],"constraint":[115],"Bregman":[122],"divergence-based":[123],"regularizer,":[124],"obtain":[126],"proposed":[128,177],"associated":[131],"two":[133],"efficient":[134],"solvers":[135],"together":[139],"transport.":[143],"predicting":[145],"labels,":[147],"our":[148],"model":[149],"combines":[150],"output":[152],"residual":[158],"component":[159],"provided":[160],"transport,":[165],"transductive":[170],"paradigm.":[172],"Experiments":[173],"show":[174],"that":[175],"QW":[178],"applies":[180],"various":[182],"GNNs":[183],"helps":[185],"improve":[187],"performance":[189],"classification":[192],"regression":[194],"tasks.":[195],"code":[197],"work":[200],"can":[201],"be":[202],"found":[203],"at":[204],"https://github.com/SDS-Lab/QW_Loss.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}