{"id":"https://openalex.org/W7159675887","doi":"https://doi.org/10.48550/arxiv.2604.27356","title":"TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks","display_name":"TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7159675887","doi":"https://doi.org/10.48550/arxiv.2604.27356"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27356","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.27356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022009228","display_name":"Ta-Yang Wang","orcid":"https://orcid.org/0000-0003-4445-8710"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ta-Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134991754","display_name":"Rajgopal Kannan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kannan, Rajgopal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134955184","display_name":"Viktor Prasanna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasanna, Viktor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.9905999898910522,"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":0.9905999898910522,"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":0.0013000000035390258,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/bottleneck","display_name":"Bottleneck","score":0.5870000123977661},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5281999707221985},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49000000953674316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48840001225471497},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.475600004196167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42910000681877136},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.41659998893737793},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.3815000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.475600004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46779999136924744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.41659998893737793},{"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/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3677000105381012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.3330000042915344},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2778459887","wikidata":"https://www.wikidata.org/wiki/Q6787865","display_name":"Matrix completion","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27356","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.27356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27356","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Heterogeneous":[0],"graphs":[1],"are":[2,231],"widely":[3],"used":[4],"to":[5],"model":[6],"multi-relational":[7],"systems,":[8],"but":[9,199],"missing":[10],"node":[11,34,80],"attributes":[12],"remain":[13],"a":[14,53,74,139,149,167,180,188,215],"major":[15],"bottleneck":[16],"for":[17,43,57,124,153,218],"downstream":[18],"learning.":[19,71],"In":[20],"this":[21,48],"paper,":[22],"we":[23,50],"identify":[24],"and":[25,68,88,122,162,194,208,228],"formalize":[26],"type-dependent":[27],"information":[28,224],"asymmetry:":[29],"the":[30,90,105,118],"phenomenon":[31],"that":[32,171],"different":[33,38],"types":[35],"provide":[36],"substantially":[37],"levels":[39],"of":[40,131],"useful":[41],"signal":[42],"attribute":[44,59,220],"completion.":[45,60],"Motivated":[46],"by":[47],"observation,":[49],"propose":[51],"TypeBandit,":[52],"lightweight,":[54],"model-agnostic":[55],"methodology":[56],"heterogeneous":[58,126,141,155,219],"TypeBandit":[61,116,132,146,196,213],"combines":[62,172],"topology-aware":[63],"initialization,":[64],"type-level":[65],"bandit":[66],"sampling,":[67],"joint":[69],"representation":[70,100],"It":[72],"allocates":[73],"finite":[75],"global":[76],"sampling":[77,229],"budget":[78],"across":[79],"types,":[81],"samples":[82],"representative":[83,154],"nodes":[84],"within":[85],"each":[86,111],"type,":[87],"uses":[89],"resulting":[91],"sampled":[92,209],"type":[93,106],"summaries":[94],"as":[95,148,214],"shared":[96],"contextual":[97],"signals":[98],"during":[99],"construction.":[101],"By":[102],"operating":[103],"at":[104],"level":[107],"rather":[108],"than":[109,137,184],"over":[110],"target":[112],"node's":[113],"local":[114],"neighborhood,":[115],"keeps":[117],"adaptive":[119],"state":[120],"compact":[121],"practical":[123,216],"large":[125],"graphs.":[127],"A":[128],"key":[129],"advantage":[130],"is":[133,225],"architectural":[134],"flexibility.":[135],"Rather":[136],"requiring":[138],"new":[140],"graph":[142],"neural":[143],"network":[144],"architecture,":[145],"acts":[147],"type-aware":[150],"front":[151],"end":[152],"GNN":[156],"backbones,":[157],"including":[158],"R-GCN,":[159],"HetGNN,":[160],"HGT,":[161],"SimpleHGN.":[163],"We":[164],"further":[165],"introduce":[166],"hybrid":[168],"pretraining":[169],"scheme":[170],"structural":[173],"degree":[174],"priors":[175],"with":[176],"feature":[177],"propagation,":[178],"yielding":[179],"more":[181],"reliable":[182],"initializer":[183],"degree-only":[185],"pretraining.":[186],"Under":[187],"fixed-split":[189],"protocol":[190],"on":[191],"DBLP,":[192],"IMDB,":[193],"ACM,":[195],"provides":[197],"dataset-dependent":[198],"practically":[200],"meaningful":[201],"gains.":[202],"Additional":[203],"ablation,":[204],"stability,":[205],"efficiency,":[206],"semantic-propagation,":[207],"OGBN-MAG":[210],"experiments":[211],"support":[212],"strategy":[217],"completion":[221],"when":[222],"type-specific":[223],"unevenly":[226],"distributed":[227],"resources":[230],"limited.":[232]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-02T00:00:00"}