{"id":"https://openalex.org/W7105656248","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227568","title":"Improving Graph Contrastive Learning with LLMs: A New Hardness-Aware Negative Sampling Strategy","display_name":"Improving Graph Contrastive Learning with LLMs: A New Hardness-Aware Negative Sampling Strategy","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105656248","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227568"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":null,"display_name":"Shuai Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhong","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaotong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haorui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haorui Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinming Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanxing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxing Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"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":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8618000149726868,"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":0.8618000149726868,"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":0.03539999946951866,"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":0.008899999782443047,"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/leverage","display_name":"Leverage (statistics)","score":0.621999979019165},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4862000048160553},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4731999933719635},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.37369999289512634},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3684000074863434},{"id":"https://openalex.org/keywords/language-acquisition","display_name":"Language acquisition","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434000134468079},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.613099992275238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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","display_name":"Quality Education","score":0.6917482614517212}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2153959628","https://openalex.org/W2154851992","https://openalex.org/W2962756421","https://openalex.org/W2970641574","https://openalex.org/W3095746859","https://openalex.org/W3154155788","https://openalex.org/W3188982020","https://openalex.org/W4221166060","https://openalex.org/W4320828694","https://openalex.org/W4382466430","https://openalex.org/W4383468961","https://openalex.org/W4385567636","https://openalex.org/W4391583896","https://openalex.org/W4391940775","https://openalex.org/W4393147769","https://openalex.org/W4393153659","https://openalex.org/W4401857389","https://openalex.org/W4402670285","https://openalex.org/W4402683734","https://openalex.org/W4402753852"],"related_works":[],"abstract_inverted_index":{"Graph":[0,90],"contrastive":[1,34],"learning":[2,35],"plays":[3],"a":[4,20,67,83],"crucial":[5],"role":[6],"in":[7,24],"many":[8],"fields,":[9],"such":[10],"as":[11],"social":[12],"network":[13],"analysis":[14],"and":[15,17,60,77,107,129,148,153],"recommendation,":[16],"has":[18],"become":[19],"hot":[21],"research":[22],"area":[23],"recent":[25],"years.":[26],"The":[27],"key":[28],"to":[29,37,72,139],"improving":[30],"the":[31,44,48,97,100,120,151],"quality":[32],"of":[33,47,66,116,155],"is":[36],"obtain":[38],"high-quality":[39],"sample":[40,55],"pairs":[41],"that":[42,99],"reflect":[43],"structural":[45],"features":[46],"data":[49,141],"more":[50],"effectively.":[51],"Existing":[52],"methods":[53],"typically":[54],"based":[56],"on":[57],"node":[58],"similarity":[59],"can":[61],"only":[62],"select":[63],"negative":[64,114,128],"samples":[65,115],"fixed":[68],"difficulty":[69],"level,":[70],"leading":[71],"issues":[73],"like":[74],"false":[75,78,127,130],"positives":[76],"negatives.":[79],"This":[80],"study":[81],"proposes":[82],"novel":[84],"paradigm":[85],"called":[86],"Hardness-aware":[87],"Negative":[88],"Sampling":[89],"Contrastive":[91],"Learning":[92],"with":[93,142],"LLMs.":[94],"We":[95],"outline":[96],"criteria":[98],"adaptive":[101],"hardness":[102,118],"sampling":[103],"method":[104,124],"should":[105],"follow":[106],"provide":[108],"concrete":[109],"instances.":[110],"By":[111],"adaptively":[112],"selecting":[113],"appropriate":[117],"during":[119],"training":[121],"process,":[122],"this":[123],"effectively":[125],"mitigates":[126],"positive":[131],"problems.":[132],"Additionally,":[133],"we":[134],"leverage":[135],"large":[136],"language":[137],"models":[138],"integrate":[140],"supplementary":[143],"textual":[144],"attributes.":[145],"Extensive":[146],"experiments":[147],"analyses":[149],"demonstrate":[150],"superiority":[152],"effectiveness":[154],"our":[156],"proposed":[157],"method.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}