{"id":"https://openalex.org/W4412825844","doi":"https://doi.org/10.1145/3711896.3736991","title":"GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations","display_name":"GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412825844","doi":"https://doi.org/10.1145/3711896.3736991"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3736991","pdf_url":null,"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":"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/A5102336987","display_name":"Junze 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":"Junze Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9619-5492","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060417049","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0001-7821-0030"},"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":"Cheng Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7821-0030","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081106841","display_name":"Shujie Li","orcid":"https://orcid.org/0009-0000-6850-3032"},"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":"Shujie Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6850-3032","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032099283","display_name":"Zhiqiang Zhang","orcid":"https://orcid.org/0000-0002-2321-7259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiqiang Zhang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2321-7259","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633553","display_name":"Yawen Li","orcid":"https://orcid.org/0000-0003-2662-3444"},"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":"Yawen Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2662-3444","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663191","display_name":"Junping Du","orcid":"https://orcid.org/0000-0002-9402-3806"},"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":"Junping Du","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9402-3806","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"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":"Chuan Shi","raw_affiliation_strings":["Beijing University of Post and Telecommunication, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3734-0266","affiliations":[{"raw_affiliation_string":"Beijing University of Post and Telecommunication, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"191","last_page":"202"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9973999857902527,"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":0.8306650519371033},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7086242437362671},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.520317792892456},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3821659982204437},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37111151218414307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306650519371033},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7086242437362671},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.520317792892456},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3821659982204437},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37111151218414307},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3736991","pdf_url":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2162630660","https://openalex.org/W2990138404","https://openalex.org/W3012562343","https://openalex.org/W3080997787","https://openalex.org/W3095746859","https://openalex.org/W3130828726","https://openalex.org/W3154503084","https://openalex.org/W3154679372","https://openalex.org/W3185341429","https://openalex.org/W3192448376","https://openalex.org/W3202105401","https://openalex.org/W3212640459","https://openalex.org/W4221023051","https://openalex.org/W4280534475","https://openalex.org/W4290876361","https://openalex.org/W4290877635","https://openalex.org/W4290993847","https://openalex.org/W4321479940","https://openalex.org/W4327525152","https://openalex.org/W4367046771","https://openalex.org/W4376864968","https://openalex.org/W4380136659","https://openalex.org/W4383468961","https://openalex.org/W4393277515","https://openalex.org/W4396722529","https://openalex.org/W6604032921"],"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":{"Large":[0],"language":[1,22,217],"models":[2,23],"(LLMs)":[3],"have":[4,13],"demonstrated":[5],"their":[6],"strong":[7],"capabilities":[8],"in":[9,46,110,142,154,286],"various":[10],"domains,":[11],"and":[12,40,87,134,148,165,172,216,241,270],"been":[14],"recently":[15],"integrated":[16],"for":[17,102,144,169,175,227],"graph":[18,21,133,182],"analysis":[19],"as":[20,27,53,70,211],"(GLMs).":[24],"With":[25],"LLMs":[26],"the":[28,47,95,176,199,220,228,249],"predictor,":[29],"some":[30],"GLMs":[31,60,129],"can":[32,105,126,207,294],"interpret":[33],"unseen":[34,132],"tasks":[35,235],"described":[36],"by":[37],"natural":[38],"language,":[39],"learn":[41],"from":[42],"a":[43,138,181,212,253],"few":[44,139,254],"examples":[45],"prompts":[48],"without":[49],"parameter":[50,122],"tuning,":[51],"known":[52,69],"in-context":[54],"learning":[55,166],"(ICL).":[56],"Another":[57],"subset":[58],"of":[59,98,202,214],"utilizes":[61],"abundant":[62],"training":[63],"labels":[64],"to":[65,84,91,108,118,130,195,244],"enhance":[66],"model":[67,163,177,224],"performance,":[68],"instruction":[71,103],"tuning.":[72],"However,":[73],"we":[74,116,157,179],"argue":[75],"that":[76,125,274],"ICL":[77],"on":[78,261,266,306],"graphs":[79],"has":[80],"effectiveness":[81],"issues":[82,89],"due":[83,90],"fixed":[85],"parameters":[86,225,256],"efficiency":[88],"long":[92],"context.":[93],"Meanwhile,":[94],"large":[96],"amount":[97],"labeled":[99,140],"data":[100],"required":[101],"tuning":[104,171],"be":[106,209,231,258,295],"difficult":[107],"obtain":[109],"real-world":[111],"scenarios.":[112],"To":[113],"this":[114,155],"end,":[115],"aim":[117],"introduce":[119],"an":[120,131],"extra":[121],"adaptation":[123,250],"stage":[124],"efficiently":[127],"tailor":[128],"task":[135],"with":[136,161,186,233,282,289],"only":[137,252],"examples,":[141],"exchange":[143],"better":[145],"prediction":[146],"accuracy":[147],"faster":[149,298],"inference":[150,292],"speed.":[151],"For":[152],"implementation,":[153],"paper":[156],"propose":[158],"GraphLAMA":[159,277],"method,":[160],"its":[162],"backbone":[164],"schemes":[167],"specialized":[168],"efficient":[170],"inference.":[173],"Specifically,":[174],"backbone,":[178],"use":[180],"neural":[183],"network":[184],"(GNN)":[185],"several":[187],"well-designed":[188],"components":[189],"(e.g.,":[190],"hop":[191],"encodings,":[192],"gating":[193],"modules)":[194],"transform":[196],"nodes":[197],"into":[198],"representation":[200],"space":[201],"LLM":[203,229],"tokens.":[204,218],"Task":[205],"instructions":[206],"then":[208],"represented":[210],"mixture":[213],"node":[215,237,239,268],"In":[219,248],"pre-training":[221],"stage,":[222,251],"all":[223],"except":[226],"will":[230,257],"trained":[232],"different":[234],"(i.e.,":[236],"matching,":[238],"classification,":[240],"link":[242],"prediction)":[243],"capture":[245],"general":[246],"knowledge.":[247],"pre-trained":[255],"updated":[259],"based":[260],"few-shot":[262],"examples.":[263],"Extensive":[264],"experiments":[265],"few/zero-shot":[267],"classification":[269],"summary":[271],"generation":[272],"show":[273],"our":[275,291],"proposed":[276],"achieves":[278],"state-of-the-art":[279],"(SOTA)":[280],"performance":[281],"4.91%":[283],"absolute":[284],"improvement":[285],"accuracy.":[287],"Compared":[288],"ICL,":[290],"speed":[293],"10":[296],"times":[297],"under":[299],"5-shot":[300],"setting.":[301],"Our":[302],"code":[303],"is":[304],"available":[305],"GitHub":[307],"at":[308],"https://github.com/BUPT-GAMMA/GraphLAMA.":[309]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}