{"id":"https://openalex.org/W7138524127","doi":"https://doi.org/10.1609/aaai.v40i34.40133","title":"THGB: A Comprehensive Benchmark for Text-attributed Heterogeneous Graphs","display_name":"THGB: A Comprehensive Benchmark for Text-attributed Heterogeneous Graphs","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138524127","doi":"https://doi.org/10.1609/aaai.v40i34.40133"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i34.40133","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40133","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i34.40133","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129736381","display_name":"Lixin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lixin Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697103","display_name":"Zemin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zemin Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650119","display_name":"Yuan Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Fang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692486","display_name":"Dan Niu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Niu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129678125","display_name":"Jing Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Ying","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129736381"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68806849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"34","first_page":"28973","last_page":"28981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9431999921798706,"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":0.9431999921798706,"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":0.02810000069439411,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.006399999838322401,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7982000112533569},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.767799973487854},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4950999915599823},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/heterogeneous-network","display_name":"Heterogeneous network","score":0.3864000141620636},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3580000102519989},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3147999942302704}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7982000112533569},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.767799973487854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760200023651123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5120000243186951},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4853000044822693},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4032000005245209},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.3864000141620636},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C137753397","wikidata":"https://www.wikidata.org/wiki/Q2434424","display_name":"Network science","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i34.40133","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40133","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i34.40133","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i34.40133","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6788083910942078,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-attributed":[0,67],"heterogeneous":[1,36,76,146],"graphs":[2,77],"(TAHGs),":[3],"characterized":[4],"by":[5,85],"nodes":[6],"interconnected":[7],"through":[8],"diverse":[9,79],"relationships":[10],"and":[11,30,105,111,122,133,148,158,166],"enriched":[12,84],"with":[13,35,81],"textual":[14,149],"descriptions,":[15],"are":[16],"prevalent":[17],"in":[18,24],"numerous":[19],"real-world":[20],"applications.":[21],"Recent":[22],"advancements":[23],"integrating":[25],"pre-trained":[26],"language":[27,32],"models":[28,33],"(PLMs)":[29],"large":[31],"(LLMs)":[34],"graph":[37,99],"neural":[38],"networks":[39],"(HGNNs)":[40],"have":[41],"enhanced":[42],"learning":[43,100,124],"on":[44],"TAHGs.":[45],"However,":[46],"the":[47,66,143],"absence":[48],"of":[49,75,145],"standardized":[50,164],"benchmark":[51,95,165],"datasets":[52],"tailored":[53],"to":[54,126,130,141],"TAHGs":[55,170],"has":[56],"impeded":[57],"further":[58],"progress.":[59],"To":[60],"bridge":[61],"this":[62],"gap,":[63],"we":[64,92],"propose":[65],"Heterogeneous":[68],"Graphs":[69],"Benchmark":[70],"(THGB),":[71],"a":[72,163],"comprehensive":[73],"collection":[74],"from":[78],"domains,":[80],"each":[82],"node":[83,109],"relevant":[86],"text":[87],"attributes.":[88],"Alongside":[89],"dataset":[90],"construction,":[91],"conduct":[93],"extensive":[94],"experiments":[96,137],"using":[97],"various":[98],"methods,":[101],"including":[102],"GNN,":[103],"PLM-GNN,":[104],"LLM-GNN":[106],"approaches,":[107],"for":[108,169],"classification":[110],"link":[112],"prediction":[113],"tasks.":[114],"We":[115],"evaluated":[116],"model":[117],"performance":[118],"across":[119],"supervised,":[120],"few-shot,":[121],"zero-shot":[123],"scenarios":[125],"assess":[127],"their":[128],"ability":[129],"leverage":[131],"limited":[132],"unseen":[134],"data.":[135],"Our":[136],"highlight":[138],"THGB's":[139],"potential":[140],"improve":[142],"integration":[144],"structural":[147],"information.":[150],"By":[151],"providing":[152],"curated":[153],"datasets,":[154],"robust":[155],"evaluation":[156],"protocols,":[157],"baseline":[159],"implementations,":[160],"THGB":[161],"introduces":[162],"solid":[167],"groundwork":[168],"research.":[171]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}