{"id":"https://openalex.org/W4412876852","doi":"https://doi.org/10.1145/3711896.3736922","title":"Efficient End-to-end Language Model Fine-tuning on Graphs","display_name":"Efficient End-to-end Language Model Fine-tuning on Graphs","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876852","doi":"https://doi.org/10.1145/3711896.3736922"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736922","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736922","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/10.1145/3711896.3736922","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518901","display_name":"Rui Xue","orcid":"https://orcid.org/0009-0003-4975-1585"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Xue","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0009-0003-4975-1585","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0003-3599-8010","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039743876","display_name":"Ruozhou Yu","orcid":"https://orcid.org/0000-0003-0905-5158"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruozhou Yu","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0003-0905-5158","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621795","display_name":"Xiaorui Liu","orcid":"https://orcid.org/0000-0001-8217-5688"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorui Liu","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"raw_orcid":"https://orcid.org/0000-0001-8217-5688","affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101518901"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":2.1733,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89620066,"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":"3449","last_page":"3460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.685313880443573},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6489889621734619},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2389008104801178}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.685313880443573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489889621734619},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2389008104801178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736922","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736922","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736922","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736922","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736922","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876852.pdf","grobid_xml":"https://content.openalex.org/works/W4412876852.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2162630660","https://openalex.org/W2920277907","https://openalex.org/W2990138404","https://openalex.org/W3085131702","https://openalex.org/W3087257704","https://openalex.org/W3167241034","https://openalex.org/W3196261868","https://openalex.org/W3202105401","https://openalex.org/W3208180646","https://openalex.org/W3212640459","https://openalex.org/W4284896159","https://openalex.org/W4386804245","https://openalex.org/W4391558151","https://openalex.org/W4400524696","https://openalex.org/W4401024755","https://openalex.org/W6782808188","https://openalex.org/W6839395506"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Learning":[0],"from":[1,63,97],"Text-Attributed":[2],"Graphs":[3],"(TAGs)":[4],"has":[5,24],"attracted":[6],"significant":[7],"attention":[8],"due":[9],"to":[10,37,99,164],"its":[11,174],"wide":[12],"range":[13],"of":[14,20,83,112,167],"real-world":[15],"applications.":[16],"The":[17],"rapid":[18],"evolution":[19],"language":[21,84],"models":[22,85],"(LMs)":[23],"revolutionized":[25],"the":[26,153],"way":[27],"we":[28,50,72,172],"process":[29],"textual":[30],"data,":[31],"which":[32],"indicates":[33],"a":[34,75,117,181],"strong":[35],"potential":[36],"replace":[38],"shallow":[39],"text":[40,58],"embedding":[41],"generally":[42],"used":[43],"in":[44,60,116],"Graph":[45],"Neural":[46],"Networks":[47],"(GNNs).":[48],"However,":[49],"find":[51],"that":[52,56],"existing":[53],"LM":[54],"approaches":[55],"exploit":[57],"information":[59],"graphs":[61],"suffer":[62],"inferior":[64],"computation":[65,124,158,176],"and":[66,77,114,135,160,177,187],"data":[67,90,107,178],"efficiency.":[68],"In":[69],"this":[70],"study,":[71],"introduce":[73],"LEADING,":[74],"novel":[76],"efficient":[78],"approach":[79,144],"for":[80,184],"end-to-end":[81,110],"fine-tuning":[82,166],"on":[86,152,191],"TAGs.":[87,192],"To":[88,121],"enhance":[89],"efficiency,":[91,179],"LEADING":[92],"efficiently":[93],"transfers":[94],"rich":[95],"knowledge":[96],"LMs":[98,113,134,186],"downstream":[100],"graph":[101,137,188],"learning":[102,119,189],"tasks":[103,190],"with":[104],"limited":[105],"labeled":[106],"by":[108],"employing":[109],"training":[111],"GNNs":[115],"semi-supervised":[118],"setting.":[120],"address":[122],"associated":[123],"efficiency":[125],"issues,":[126],"it":[127],"introduces":[128],"two":[129],"techniques:":[130],"neighbor":[131],"decoupling":[132],"targeting":[133,139],"implicit":[136],"modeling":[138],"GNNs,":[140],"respectively.":[141],"Our":[142],"proposed":[143],"demonstrates":[145],"superior":[146,175],"performance,":[147],"achieving":[148],"state-of-the-art":[149],"(SOTA)":[150],"results":[151],"ogbn-arxiv":[154],"leaderboard,":[155],"while":[156],"maintaining":[157],"cost":[159],"memory":[161],"overhead":[162],"comparable":[163],"graph-less":[165],"LMs.":[168],"Through":[169],"comprehensive":[170],"experiments,":[171],"showcase":[173],"presenting":[180],"promising":[182],"solution":[183],"various":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}