{"id":"https://openalex.org/W4385568277","doi":"https://doi.org/10.1145/3580305.3599833","title":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications","display_name":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568277","doi":"https://doi.org/10.1145/3580305.3599833","pmid":"https://pubmed.ncbi.nlm.nih.gov/38375450"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599833","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007293006","display_name":"Han Xie","orcid":"https://orcid.org/0000-0001-7633-5040"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Han Xie","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060763203","display_name":"Da Zheng","orcid":"https://orcid.org/0000-0001-8115-5415"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Zheng","raw_affiliation_strings":["Amazon AWS AI, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643102","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0003-4679-9500"},"institutions":[{"id":"https://openalex.org/I3007373383","display_name":"Walgreens (United States)","ror":"https://ror.org/00615jn62","country_code":"US","type":"company","lineage":["https://openalex.org/I3007373383"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Walgreens AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Walgreens AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I3007373383","https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028155676","display_name":"Houyu Zhang","orcid":"https://orcid.org/0009-0006-4579-0685"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houyu Zhang","raw_affiliation_strings":["Amazon Search AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023028617","display_name":"Vassilis N. Ioannidis","orcid":"https://orcid.org/0000-0002-8367-0733"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vassilis N. Ioannidis","raw_affiliation_strings":["Amazon Search AI, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675531","display_name":"Xiang Song","orcid":"https://orcid.org/0000-0001-5030-5054"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Song","raw_affiliation_strings":["Amazon AWS AI, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon AWS AI, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047553143","display_name":"Qing Ping","orcid":"https://orcid.org/0000-0002-8919-9364"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Ping","raw_affiliation_strings":["Amazon Search AI, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048356362","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0002-0439-5199"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["Amazon Scholar, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Scholar, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006897094","display_name":"Carl Yang","orcid":"https://orcid.org/0000-0001-9145-4531"},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Yang","raw_affiliation_strings":["Emory University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Emory University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035425640","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-0604-8481"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Amazon Search AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082750097","display_name":"Belinda Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Belinda Zeng","raw_affiliation_strings":["Amazon Search AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013670321","display_name":"Trishul Chilimbi","orcid":"https://orcid.org/0000-0001-6711-1117"},"institutions":[{"id":"https://openalex.org/I4210133358","display_name":"Search","ror":"https://ror.org/03f78hn46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210133358"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trishul Chilimbi","raw_affiliation_strings":["Amazon Search AI, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search AI, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210133358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5007293006"],"corresponding_institution_ids":["https://openalex.org/I150468666"],"apc_list":null,"apc_paid":null,"fwci":3.7312,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94531544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"2023","issue":null,"first_page":"5270","last_page":"5281"},"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.8229720592498779},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5375658273696899},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5028747916221619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44961637258529663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38531729578971863},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3668358027935028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229720592498779},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5375658273696899},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5028747916221619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44961637258529663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38531729578971863},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3668358027935028}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3580305.3599833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599833","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmid:38375450","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38375450","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"KDD : proceedings. International Conference on Knowledge Discovery & Data Mining","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10876412","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10876412","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10876412/pdf/nihms-1964224.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599833","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599833","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599833","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568277.pdf","grobid_xml":"https://content.openalex.org/works/W4385568277.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2604314403","https://openalex.org/W2911286998","https://openalex.org/W2962946486","https://openalex.org/W3012871709","https://openalex.org/W3034999214","https://openalex.org/W3036446966","https://openalex.org/W3080997787","https://openalex.org/W3090656107","https://openalex.org/W3099152386","https://openalex.org/W3105082862","https://openalex.org/W3114303065","https://openalex.org/W3125508839","https://openalex.org/W3156738579","https://openalex.org/W3166423611","https://openalex.org/W3170268576","https://openalex.org/W3174146526","https://openalex.org/W3176175717","https://openalex.org/W3208743992","https://openalex.org/W6601782648"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3136979370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Model":[0],"pre-training":[1,30,61,105],"on":[2,33,67,84,107,127,134],"large":[3,34,68,76,109,114,140],"text":[4,63],"corpora":[5],"has":[6,45,57],"been":[7,47],"demonstrated":[8],"effective":[9],"for":[10,29],"various":[11],"downstream":[12,41,87,128],"applications":[13,88],"in":[14,36],"the":[15,19,37,60,82,150],"NLP":[16],"domain.":[17],"In":[18],"graph":[20,31,42,65,77,91,110,118],"mining":[21],"domain,":[22],"a":[23,99,108,122],"similar":[24],"analogy":[25],"can":[26],"be":[27],"drawn":[28],"models":[32,66,116],"graphs":[35,70],"hope":[38],"of":[39,62,101,124,152],"benefiting":[40],"applications,":[43],"which":[44,112],"also":[46],"explored":[48],"by":[49],"several":[50],"recent":[51],"studies.":[52],"However,":[53],"no":[54],"existing":[55],"study":[56],"ever":[58],"investigated":[59],"plus":[64],"heterogeneous":[69],"with":[71,89,157],"abundant":[72],"textual":[73],"information":[74],"(a.k.a.":[75],"corpora)":[78],"and":[79,117,121,139,146],"then":[80],"fine-tuning":[81,125],"model":[83,104],"different":[85,90],"related":[86],"schemas.":[92],"To":[93],"address":[94],"this":[95],"problem,":[96],"we":[97],"propose":[98],"framework":[100],"graph-aware":[102],"language":[103,115],"(GaLM)":[106],"corpus,":[111],"incorporates":[113],"neural":[119],"networks,":[120],"variety":[123],"methods":[126,155],"applications.":[129],"We":[130],"conduct":[131],"extensive":[132],"experiments":[133],"Amazon's":[135],"real":[136],"internal":[137],"datasets":[138],"public":[141],"datasets.":[142],"Comprehensive":[143],"empirical":[144],"results":[145],"in-depth":[147],"analysis":[148],"demonstrate":[149],"effectiveness":[151],"our":[153],"proposed":[154],"along":[156],"lessons":[158],"learned.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}