{"id":"https://openalex.org/W4396820377","doi":"https://doi.org/10.48550/arxiv.2404.18271","title":"Parameter-Efficient Tuning Large Language Models for Graph Representation Learning","display_name":"Parameter-Efficient Tuning Large Language Models for Graph Representation Learning","publication_year":2024,"publication_date":"2024-04-28","ids":{"openalex":"https://openalex.org/W4396820377","doi":"https://doi.org/10.48550/arxiv.2404.18271"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2404.18271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.18271","pdf_url":"https://arxiv.org/pdf/2404.18271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.18271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055199412","display_name":"Qi Zhu","orcid":"https://orcid.org/0000-0003-0129-8542"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101155301","display_name":"Da Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Da","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675531","display_name":"Xiang Song","orcid":"https://orcid.org/0000-0001-5030-5054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412768","display_name":"Shichang Zhang","orcid":"https://orcid.org/0000-0003-0954-5018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shichang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110948473","display_name":"Bowen Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Bowen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025213473","display_name":"Yizhou Sun","orcid":"https://orcid.org/0000-0003-1812-6843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yizhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karypis, George","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5055199412"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9930999875068665,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9735999703407288,"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/computer-science","display_name":"Computer science","score":0.6513416767120361},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5818458795547485},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5734630823135376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4237879812717438},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36773380637168884},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3368474841117859},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06262290477752686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513416767120361},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5818458795547485},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5734630823135376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4237879812717438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36773380637168884},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3368474841117859},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06262290477752686},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2404.18271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.18271","pdf_url":"https://arxiv.org/pdf/2404.18271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2404.18271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.18271","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.18271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.18271","pdf_url":"https://arxiv.org/pdf/2404.18271","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396820377.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742","https://openalex.org/W4390679071","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-rich":[0],"graphs,":[1,190],"which":[2,32],"exhibit":[3],"rich":[4],"textual":[5],"information":[6,110],"on":[7,53,96,186],"nodes":[8,113],"and":[9,73,160,199,213,233],"edges,":[10],"are":[11],"prevalent":[12],"across":[13],"a":[14,86,102,115],"wide":[15],"range":[16],"of":[17,126,134,195,215],"real-world":[18],"business":[19],"applications.":[20],"Large":[21],"Language":[22],"Models":[23],"(LLMs)":[24],"have":[25,64],"demonstrated":[26],"remarkable":[27],"abilities":[28],"in":[29,41,146,151,197,204],"understanding":[30],"text,":[31],"also":[33],"introduced":[34],"the":[35,124,127,132,139,143,148,152,166,211],"potential":[36],"for":[37,62,89],"more":[38],"expressive":[39],"modeling":[40],"text-rich":[42,97,189],"graphs.":[43,98],"Despite":[44],"these":[45],"capabilities,":[46],"efficiently":[47],"applying":[48],"LLMs":[49,63,95],"to":[50,107,141],"representation":[51,92],"learning":[52,93],"graphs":[54],"presents":[55],"significant":[56],"challenges.":[57],"Recently,":[58],"parameter-efficient":[59],"fine-tuning":[60,176],"methods":[61],"enabled":[65],"efficient":[66,90],"new":[67],"task":[68],"generalization":[69],"with":[70,94,156,173,225],"minimal":[71],"time":[72],"memory":[74],"consumption.":[75],"Inspired":[76],"by":[77],"this,":[78],"we":[79,100,137],"introduce":[80],"Graph-aware":[81],"Parameter-Efficient":[82],"Fine-Tuning":[83],"-":[84],"GPEFT,":[85],"novel":[87],"approach":[88,181],"graph":[91,103,116,135],"Specifically,":[99],"utilize":[101],"neural":[104],"network":[105],"(GNN)":[106],"encode":[108],"structural":[109],"from":[111,169],"neighboring":[112],"into":[114],"prompt.":[117],"This":[118],"prompt":[119],"is":[120],"then":[121],"inserted":[122],"at":[123],"beginning":[125],"text":[128],"sequence.":[129],"To":[130],"improve":[131],"quality":[133],"prompts,":[136],"pre-trained":[138],"GNN":[140,159],"assist":[142],"frozen":[144],"LLM":[145],"predicting":[147],"next":[149],"token":[150],"node":[153,167],"text.":[154],"Compared":[155],"existing":[157],"joint":[158],"LMs,":[161],"our":[162,180,216],"method":[163],"directly":[164],"generate":[165],"embeddings":[168],"large":[170,227],"language":[171,228],"models":[172],"an":[174,192],"affordable":[175],"cost.":[177],"We":[178],"validate":[179],"through":[182],"comprehensive":[183],"experiments":[184],"conducted":[185],"8":[187],"different":[188],"observing":[191],"average":[193],"improvement":[194],"2%":[196],"hit@1":[198],"Mean":[200],"Reciprocal":[201],"Rank":[202],"(MRR)":[203],"link":[205],"prediction":[206],"evaluations.":[207],"Our":[208],"results":[209],"demonstrate":[210],"efficacy":[212],"efficiency":[214],"model,":[217],"showing":[218],"that":[219],"it":[220],"can":[221],"be":[222],"smoothly":[223],"integrated":[224],"various":[226],"models,":[229],"including":[230],"OPT,":[231],"LLaMA":[232],"Falcon.":[234]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}