{"id":"https://openalex.org/W4411549658","doi":"https://doi.org/10.1145/3701716.3715302","title":"Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains","display_name":"Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4411549658","doi":"https://doi.org/10.1145/3701716.3715302"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","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/A5108502922","display_name":"Yun-Hui Liu","orcid":"https://orcid.org/0009-0006-3337-0886"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhui Liu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-3337-0886","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086705284","display_name":"Qizhuo Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qizhuo Xie","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-5595-6132","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinwei Shi","orcid":"https://orcid.org/0009-0009-4029-7615"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Shi","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-4029-7615","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101264105","display_name":"Jiaxu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Shen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0009-0894-2733","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027259486","display_name":"Tieke He","orcid":"https://orcid.org/0000-0001-9649-1796"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieke He","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9649-1796","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92770762,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"757","last_page":"760"},"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":0.9991999864578247,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7347465753555298},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5139536261558533},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5128486156463623},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3364436626434326},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3296118974685669},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3168308734893799},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10118767619132996},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07495930790901184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347465753555298},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5139536261558533},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5128486156463623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3364436626434326},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3296118974685669},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3168308734893799},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10118767619132996},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07495930790901184}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3701716.3715302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2893359107","https://openalex.org/W2970641574","https://openalex.org/W3002924435","https://openalex.org/W3021975806","https://openalex.org/W3100078588","https://openalex.org/W3189626311","https://openalex.org/W3204133498","https://openalex.org/W3209163300","https://openalex.org/W4285378361","https://openalex.org/W4392223764","https://openalex.org/W4401863214"],"related_works":["https://openalex.org/W4213212078","https://openalex.org/W2187227032","https://openalex.org/W2112788825","https://openalex.org/W1963735073","https://openalex.org/W4233129888","https://openalex.org/W106707639","https://openalex.org/W2146247781","https://openalex.org/W2144684733","https://openalex.org/W4299950557","https://openalex.org/W2575246084"],"abstract_inverted_index":{"Heterogeneous":[0],"Text-Attributed":[1],"Graphs":[2],"(HTAGs),":[3],"where":[4],"different":[5],"types":[6],"of":[7,67,80,90,101,121],"entities":[8],"are":[9,110,161],"not":[10],"only":[11],"associated":[12],"with":[13,141],"texts":[14],"but":[15],"also":[16],"connected":[17],"by":[18],"diverse":[19,93],"relationships,":[20],"have":[21],"gained":[22],"widespread":[23],"popularity":[24],"and":[25,47,76,92,98,116,130,158,166],"application":[26],"across":[27],"various":[28,142],"domains.":[29],"However,":[30],"current":[31],"research":[32],"on":[33,39,59,105,138],"text-attributed":[34],"graph":[35,143],"learning":[36,103],"predominantly":[37],"focuses":[38],"homogeneous":[40],"graphs,":[41],"which":[42],"feature":[43],"a":[44,52,88,118],"single":[45],"node":[46],"edge":[48],"type,":[49],"thus":[50],"leaving":[51],"gap":[53],"in":[54,114],"understanding":[55],"how":[56],"methods":[57],"perform":[58],"HTAGs.":[60,106],"One":[61],"crucial":[62],"reason":[63],"is":[64],"the":[65],"lack":[66],"comprehensive":[68],"HTAG":[69,108],"datasets":[70,95,109,140],"that":[71],"offer":[72],"original":[73],"textual":[74],"content":[75],"span":[77,112],"multiple":[78],"domains":[79],"varying":[81],"sizes.":[82],"To":[83],"this":[84],"end,":[85],"we":[86],"introduce":[87],"collection":[89],"challenging":[91],"benchmark":[94,136,156],"for":[96],"realistic":[97],"reproducible":[99],"evaluation":[100,159],"machine":[102],"models":[104],"Our":[107],"multi-scale,":[111],"years":[113],"duration,":[115],"cover":[117],"wide":[119],"range":[120],"domains,":[122],"including":[123],"movie,":[124],"community":[125],"question":[126],"answering,":[127],"academic,":[128],"literature,":[129],"patent":[131],"networks.":[132,145],"We":[133],"further":[134],"conduct":[135],"experiments":[137],"these":[139],"neural":[144],"All":[146],"source":[147],"data,":[148],"dataset":[149],"construction":[150],"codes,":[151,157],"processed":[152],"HTAGs,":[153],"data":[154],"loaders,":[155],"setup":[160],"publicly":[162],"available":[163],"at":[164],"https://github.com/Cloudy1225/HTAG":[165],"https://huggingface.co/datasets/Cloudy1225/HTAG.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}