{"id":"https://openalex.org/W4409149456","doi":"https://doi.org/10.1145/3690624.3709277","title":"UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs","display_name":"UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409149456","doi":"https://doi.org/10.1145/3690624.3709277"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709277","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3690624.3709277","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078622166","display_name":"Yufei He","orcid":"https://orcid.org/0000-0001-8918-6734"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yufei He","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399147","display_name":"Yuan Sui","orcid":"https://orcid.org/0000-0001-8559-831X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuan Sui","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078671497","display_name":"Xiaoxin He","orcid":"https://orcid.org/0000-0002-8281-8070"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaoxin He","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065675832","display_name":"Bryan Hooi","orcid":"https://orcid.org/0000-0002-5645-1754"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bryan Hooi","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078622166"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":16.402,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98792637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9925000071525574,"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/foundation","display_name":"Foundation (evidence)","score":0.6716699600219727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5599086284637451},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47037142515182495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3410795331001282},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12232735753059387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1122002899646759},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.07261574268341064}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6716699600219727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5599086284637451},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47037142515182495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3410795331001282},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12232735753059387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1122002899646759},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.07261574268341064},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709277","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3690624.3709277","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709277","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2293888960","https://openalex.org/W2798991696","https://openalex.org/W2990138404","https://openalex.org/W3036446966","https://openalex.org/W3094624443","https://openalex.org/W3099152386","https://openalex.org/W3159481202","https://openalex.org/W4206453098","https://openalex.org/W4240153047","https://openalex.org/W4283645071","https://openalex.org/W4290876361","https://openalex.org/W4298292701","https://openalex.org/W4307207329","https://openalex.org/W4312309398","https://openalex.org/W4313156423","https://openalex.org/W4319779371","https://openalex.org/W4367046771","https://openalex.org/W4367047461","https://openalex.org/W4376864968","https://openalex.org/W4401856724","https://openalex.org/W4401863472","https://openalex.org/W6600503824","https://openalex.org/W6600586173","https://openalex.org/W6600669965","https://openalex.org/W6602311867","https://openalex.org/W6846517570"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"Foundation":[0],"models":[1,125],"like":[2],"ChatGPT":[3],"and":[4,21,60,70,88,118,169,220,236],"GPT-4":[5],"have":[6,156,248],"revolutionized":[7],"artificial":[8],"intelligence,":[9],"exhibiting":[10],"remarkable":[11],"abilities":[12],"to":[13,38,46,50,74,93,103,115,207],"generalize":[14],"across":[15,120,215],"a":[16,105,161],"wide":[17],"array":[18],"of":[19,62,113,131,165,245],"tasks":[20,40,119,219],"applications":[22],"beyond":[23],"their":[24],"initial":[25],"training":[26,251],"objectives.":[27],"However,":[28],"graph":[29,63,75,199,217],"learning":[30,189,218,229],"has":[31],"predominantly":[32],"focused":[33],"on":[34,190,193,230,252],"single-graph":[35,124],"models,":[36],"tailored":[37],"specific":[39,73],"or":[41,241],"datasets,":[42],"lacking":[43],"the":[44,57,67,180,223,243],"ability":[45],"transfer":[47],"learned":[48],"knowledge":[49],"different":[51,68],"domains.":[52,122],"This":[53],"limitation":[54],"stems":[55],"from":[56],"inherent":[58],"complexity":[59],"diversity":[61],"structures,":[64],"along":[65],"with":[66],"feature":[69],"label":[71],"spaces":[72],"data.":[76],"In":[77],"this":[78,95],"paper,":[79],"we":[80,178],"recognize":[81],"text":[82],"as":[83,134,149,174],"an":[84],"effective":[85],"unifying":[86,142],"medium":[87],"employ":[89],"Text-Attributed":[90],"Graphs":[91],"(TAGs)":[92],"leverage":[94],"potential.":[96],"We":[97,159,197],"present":[98],"our":[99,136],"UniGraph":[100],"framework,":[101],"designed":[102,185],"learn":[104],"foundation":[106],"model":[107],"for":[108,141,146,186],"TAGs,":[109,191],"which":[110],"is":[111],"capable":[112],"generalizing":[114],"unseen":[116,231],"graphs":[117,147,151],"diverse":[121],"Unlike":[123],"that":[126,152,247],"use":[127],"pre-computed":[128],"node":[129,143],"features":[130,140],"varying":[132],"dimensions":[133],"input,":[135],"approach":[137],"leverages":[138],"textual":[139,157],"representations,":[144],"even":[145,239],"such":[148],"molecular":[150],"do":[153],"not":[154],"naturally":[155],"features.":[158],"propose":[160,179],"novel":[162],"cascaded":[163],"architecture":[164],"Language":[166,204],"Models":[167,205],"(LMs)":[168],"Graph":[170,195],"Neural":[171],"Networks":[172],"(GNNs)":[173],"backbone":[175],"networks.":[176],"Additionally,":[177],"first":[181],"pre-training":[182],"algorithm":[183],"specifically":[184],"large-scale":[187],"self-supervised":[188,227],"based":[192],"Masked":[194],"Modeling.":[196],"introduce":[198],"instruction":[200],"tuning":[201],"using":[202],"Large":[203],"(LLMs)":[206],"enable":[208],"zero-shot":[209,237],"prediction":[210],"ability.":[211],"Our":[212],"comprehensive":[213],"experiments":[214],"various":[216],"domains":[221],"demonstrate":[222],"model's":[224],"effectiveness":[225],"in":[226],"representation":[228],"graphs,":[232],"few-shot":[233],"in-context":[234],"transfer,":[235,238],"surpassing":[240],"matching":[242],"performance":[244],"GNNs":[246],"undergone":[249],"supervised":[250],"target":[253],"datasets.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}