{"id":"https://openalex.org/W4402352534","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650308","title":"Multi-Faceted Negative Sample Mining for Grpah Contrastive Learning","display_name":"Multi-Faceted Negative Sample Mining for Grpah Contrastive Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352534","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650308"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650308","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031544610","display_name":"Siyu Liu","orcid":"https://orcid.org/0000-0001-5192-8739"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Liu","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438235","display_name":"Ziqi Wang","orcid":"https://orcid.org/0000-0002-0232-125X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Wang","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108871777","display_name":"Jiale Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Xu","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001609648","display_name":"Huan Li","orcid":"https://orcid.org/0000-0001-7332-6122"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618776","display_name":"Jiamin Sun","orcid":"https://orcid.org/0009-0001-0692-3047"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Sun","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343656","display_name":"LI Ya","orcid":"https://orcid.org/0000-0002-1607-9919"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Southwest University,Computer and Information Science,Chongqing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"119","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T10057","display_name":"Face and Expression Recognition","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9958999752998352,"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/sample","display_name":"Sample (material)","score":0.6360891461372375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5959996581077576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32429853081703186}],"concepts":[{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6360891461372375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5959996581077576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32429853081703186},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650308","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2152195021","https://openalex.org/W2154851992","https://openalex.org/W2602856279","https://openalex.org/W2913668833","https://openalex.org/W2914304175","https://openalex.org/W2962756421","https://openalex.org/W2990138404","https://openalex.org/W3012816161","https://openalex.org/W3033039844","https://openalex.org/W3035524453","https://openalex.org/W3036446966","https://openalex.org/W3095746859","https://openalex.org/W3099152386","https://openalex.org/W3104097132","https://openalex.org/W3154503084","https://openalex.org/W3166500718","https://openalex.org/W3169827396","https://openalex.org/W4221023051","https://openalex.org/W4231449374","https://openalex.org/W4290876361","https://openalex.org/W4298053686","https://openalex.org/W4308770253","https://openalex.org/W4362691848","https://openalex.org/W4367047461","https://openalex.org/W4382466430","https://openalex.org/W6639055396","https://openalex.org/W6726873649","https://openalex.org/W6760001035","https://openalex.org/W6774314701","https://openalex.org/W6779518175","https://openalex.org/W6783961830","https://openalex.org/W6783990618","https://openalex.org/W6784694379","https://openalex.org/W6784950539","https://openalex.org/W6790763814","https://openalex.org/W6841246528"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,19,205],"has":[2],"made":[3],"tremendous":[4],"progress":[5],"in":[6,60,97],"graph":[7,67,98,148,221],"self-learning":[8],"even":[9],"surpassing":[10],"the":[11,21,76,114,124,140,183,186,191,195,201,217],"traditional":[12],"supervised":[13],"method.":[14],"The":[15],"core":[16],"of":[17,23,42,79,123,130,142,160,194,203],"contrastive":[18,27,68,99,149,204],"is":[20],"selection":[22],"negative":[24,30,44,54,96,110,128,145,162],"samples.":[25,163],"In":[26,132,164,197],"learning,":[28,69],"hard":[29,43,53,95,144],"samples":[31,45,146],"contribute":[32],"significantly":[33],"more":[34],"than":[35],"easy":[36],"negatives,":[37],"only":[38],"a":[39,89,108,158],"small":[40],"number":[41],"can":[46,72],"effectively":[47],"support":[48],"model":[49,214,231],"training.":[50],"However,":[51],"prevailing":[52],"mining":[55],"techniques":[56],"that":[57],"work":[58],"well":[59],"other":[61],"domains":[62],"bring":[63],"limited":[64],"benefits":[65],"to":[66,75,93,103,119,199,215],"this":[70,85,133],"phenomenon":[71],"be":[73],"attributed":[74],"message":[77],"passing":[78],"Graph":[80],"Neural":[81],"Networks.":[82],"To":[83],"solve":[84],"problem,":[86],"we":[87,135,211],"propose":[88],"new":[90],"sampling":[91],"method":[92],"measure":[94],"learning.":[100],"Specifically,":[101],"according":[102],"existing":[104,166,234],"practice":[105],"and":[106,155,176,206,219],"theory,":[107],"high-quality":[109],"sample":[111,129],"should":[112],"have":[113],"following":[115],"attributes:":[116],"high":[117],"similarity":[118],"anchor":[120],"features,":[121],"representation":[122],"node":[125],"population,":[126],"true":[127,161],"anchor.":[131],"work,":[134],"integrate":[136],"three":[137],"aspects":[138],"with":[139,157],"goal":[141],"improving":[143],"for":[147],"training:":[150],"representative":[151],"nodes,":[152],"feature":[153],"similarity,":[154],"nodes":[156],"probability":[159],"addition,":[165],"methods":[167],"mainly":[168],"focus":[169],"on":[170,225],"maximizing":[171],"mutual":[172],"information":[173,193,202],"between":[174,185],"diffusion":[175,218],"original":[177,192],"graphs":[178],"through":[179],"cross-learning,":[180],"but":[181],"pulling":[182],"distance":[184],"two":[187],"views":[188],"may":[189],"lose":[190],"view.":[196],"order":[198],"enrich":[200],"fully":[207],"exploit":[208],"view\u2019s":[209],"information,":[210],"utilize":[212],"dual":[213],"learn":[216],"origin":[220],"individually.":[222],"Experimental":[223],"results":[224],"five":[226],"benchmark":[227],"datasets":[228],"show":[229],"our":[230],"outperforms":[232],"most":[233],"methods.":[235]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}