{"id":"https://openalex.org/W7137818612","doi":"https://doi.org/10.1609/aaai.v40i32.39966","title":"Structure-Enhanced Adapter for Self-Supervised Heterogeneous Graph Learning","display_name":"Structure-Enhanced Adapter for Self-Supervised Heterogeneous Graph Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137818612","doi":"https://doi.org/10.1609/aaai.v40i32.39966"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i32.39966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39966","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.v40i32.39966","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062663265","display_name":"Fei Yan","orcid":"https://orcid.org/0000-0002-5870-2799"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fengyu Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718940","display_name":"Di Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662388","display_name":"Xiaobao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686142","display_name":"Qianhua Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianhua Tang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5117111494","display_name":"Dongxiao He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxiao He","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062663265"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02782236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"32","first_page":"27477","last_page":"27485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0006000000284984708,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.0006000000284984708,"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/adapter","display_name":"Adapter (computing)","score":0.6290000081062317},{"id":"https://openalex.org/keywords/heterogeneous-network","display_name":"Heterogeneous network","score":0.5796999931335449},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5428000092506409},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.43059998750686646},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.37400001287460327},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.3675000071525574},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.35120001435279846},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.3287999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095000147819519},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6290000081062317},{"id":"https://openalex.org/C158207573","wikidata":"https://www.wikidata.org/wiki/Q5747224","display_name":"Heterogeneous network","level":4,"score":0.5796999931335449},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.43059998750686646},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.37400001287460327},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i32.39966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39966","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.v40i32.39966","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39966","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":[{"display_name":"Reduced inequalities","score":0.7848363518714905,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"heterogeneous":[1,7,30,42,133,171],"data":[2],"is":[3],"commonly":[4],"modeled":[5],"as":[6],"information":[8],"networks":[9,17],"(HINs).":[10],"Building":[11],"upon":[12],"advancements":[13],"in":[14,24,40,49],"graph":[15,98,172],"neural":[16],"(GNNs),":[18],"existing":[19,62],"research":[20],"has":[21],"significantly":[22,158],"progressed":[23],"semi-supervised":[25],"and":[26,55,83,130,154,167],"self-supervised":[27],"paradigms":[28],"for":[29,110,163],"GNNs":[31],"(HGNNs).":[32],"However,":[33],"these":[34],"methods":[35],"overlook":[36],"inherent":[37],"structural":[38,47,112],"deficiencies":[39],"raw":[41],"graphs.":[43,144],"We":[44],"identifies":[45],"unique":[46],"noise":[48,78],"HINs:":[50],"missing":[51],"potential":[52],"critical":[53],"edges":[54,139],"multi-relational":[56],"semantically":[57],"redundant":[58,138],"edges,":[59],"which":[60],"force":[61],"HGNNs":[63],"to":[64],"learn":[65],"suboptimal":[66],"representations":[67],"on":[68],"fixed":[69],"topologies.":[70],"Crucially,":[71],"prior":[72],"limited":[73],"studies":[74],"address":[75],"only":[76],"partial":[77],"while":[79,108,140],"remaining":[80],"architecturally":[81],"entrenched":[82],"tightly":[84],"coupled":[85],"with":[86,114,115],"specific":[87],"models.":[88,175],"To":[89],"break":[90],"this":[91],"bottleneck,":[92],"we":[93],"propose":[94],"a":[95,119,131],"plug-and-play":[96],"Heterogeneous":[97],"Structure":[99],"ADaPter":[100],"(HSADP)":[101],"that":[102],"simultaneously":[103],"resolves":[104],"task/model":[105],"decoupling":[106],"challenges":[107],"accounting":[109],"HIN-specific":[111],"properties":[113],"two":[116],"core":[117],"components:":[118],"dynamic":[120],"homogeneous":[121],"subgraph":[122],"enhancer":[123],"recovering":[124],"latent":[125],"topology":[126],"across":[127,147],"semantic":[128,143],"views":[129],"learnable":[132],"edge":[134],"discriminator":[135],"dynamically":[136],"suppressing":[137],"collaboratively":[141],"optimizing":[142],"Extensive":[145],"experiments":[146],"multi-domain":[148],"datasets":[149],"demonstrate":[150],"our":[151],"method\u2019s":[152],"effectiveness":[153],"compatibility.":[155],"The":[156],"adapter":[157],"boosts":[159],"node":[160],"classification":[161],"accuracy":[162],"multiple":[164],"SOTA":[165],"approaches":[166],"surpasses":[168],"specially":[169],"designed":[170],"structure":[173],"learning":[174]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}