{"id":"https://openalex.org/W7167091014","doi":"https://doi.org/10.48550/arxiv.2607.00052","title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","display_name":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7167091014","doi":"https://doi.org/10.48550/arxiv.2607.00052"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00052","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00052","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.00052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139895289","display_name":"Bao Long Nguyen Huu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huu, Bao Long Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139908041","display_name":"Atsushi Hashimoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hashimoto, Atsushi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.72079998254776,"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":0.72079998254776,"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":0.15070000290870667,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05620000138878822,"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/embedding","display_name":"Embedding","score":0.6180999875068665},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4887999892234802},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4253000020980835},{"id":"https://openalex.org/keywords/graph-embedding","display_name":"Graph embedding","score":0.40630000829696655},{"id":"https://openalex.org/keywords/graph-kernel","display_name":"Graph kernel","score":0.39820000529289246},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.37630000710487366},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3427000045776367},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6717000007629395},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6180999875068665},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5784000158309937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.39820000529289246},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C163173736","wikidata":"https://www.wikidata.org/wiki/Q3308558","display_name":"Key generation","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.2623000144958496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00052","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00052","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.00052","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00052","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7474554181098938,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"GraphRAG":[0],"is":[1],"an":[2],"extension":[3],"of":[4],"retrieval-augmented":[5],"generation":[6],"(RAG)":[7],"that":[8,105,148],"supports":[9],"large":[10],"language":[11,93],"models":[12],"(LLMs)":[13],"by":[14,55],"referring":[15],"to":[16,42,80,91,113,123],"graph-structured":[17],"data":[18],"as":[19],"external":[20],"knowledge.":[21],"While":[22],"this":[23,53],"technique":[24],"ideally":[25],"captures":[26],"intricate":[27],"relationships,":[28],"it":[29],"often":[30],"struggles":[31],"with":[32,167],"graph":[33],"representations":[34],"for":[35,38,60],"LLMs,":[36,40],"particularly":[37],"frozen":[39],"due":[41],"the":[43,57,77,85,126],"misalignment":[44],"between":[45],"graph-based":[46],"and":[47,99],"text-based":[48],"latent":[49,86],"features.":[50],"We":[51,75],"tackle":[52],"issue":[54],"introducing":[56],"{\\it":[58,102],"Adaptive-masking":[59],"Graph":[61],"Embedding":[62],"(AGE)}.":[63],"AGE":[64,130,149],"employs":[65],"a":[66,69,140],"Transformer":[67],"in":[68,125,157],"mask-based":[70],"self-supervised":[71],"learning":[72],"(SSL)":[73],"approach.":[74],"designed":[76],"architecture":[78],"similar":[79],"text":[81],"embedding":[82],"encoders,":[83],"addressing":[84],"feature":[87],"misalignment.":[88],"In":[89],"contrast":[90],"natural":[92],"texts,":[94],"graphs":[95],"are":[96,111],"concise":[97],"representations,":[98],"there":[100],"exist":[101],"key":[103,120,137],"nodes}":[104],"hold":[106],"dominant":[107],"contextual":[108],"information,":[109],"which":[110],"challenging":[112],"predict":[114],"from":[115,136],"their":[116],"surroundings.":[117],"Masking":[118],"such":[119],"nodes":[121,134],"leads":[122],"inefficiency":[124],"SSL":[127],"process.":[128],"Therefore,":[129],"focuses":[131],"on":[132],"predicting":[133],"apart":[135],"nodes,":[138],"utilizing":[139],"learnable":[141],"node":[142],"sampler.":[143],"Our":[144],"experimental":[145],"results":[146],"indicate":[147],"significantly":[150],"improves":[151],"approaches":[152],"using":[153],"non-parametric":[154],"search":[155],"component":[156],"GraphQA":[158],"tasks,":[159],"achieving":[160],"superior":[161],"accuracy":[162],"across":[163],"four":[164],"benchmark":[165],"datasets":[166],"distinct":[168],"characteristics.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}