{"id":"https://openalex.org/W4416631836","doi":"https://doi.org/10.48550/arxiv.2511.13062","title":"Self-Adaptive Graph Mixture of Models","display_name":"Self-Adaptive Graph Mixture of Models","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416631836","doi":"https://doi.org/10.48550/arxiv.2511.13062"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.13062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.13062","pdf_url":"https://arxiv.org/pdf/2511.13062","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.13062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045157128","display_name":"Mohit Kumar Meena","orcid":"https://orcid.org/0000-0001-9171-2641","observed_orcids":["https://orcid.org/0000-0001-9171-2641"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meena, Mohit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120472106","display_name":"Yash Punjabi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Punjabi, Yash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728750","display_name":"Abhishek Abhishek","orcid":"https://orcid.org/0000-0003-0121-4919","observed_orcids":["https://orcid.org/0000-0003-0121-4919"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A, Abhishek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060650984","display_name":"Vishal Sharma","orcid":"https://orcid.org/0000-0002-5130-1626","observed_orcids":["https://orcid.org/0000-0002-5130-1626","https://orcid.org/0009-0004-4389-7820"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Vishal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123201471","display_name":"Mahesh Chandran","orcid":"https://orcid.org/0000-0003-3997-2301","observed_orcids":["https://orcid.org/0000-0003-3997-2301"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandran, Mahesh","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":true,"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":1.0,"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":1.0,"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":0.0,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.9380000233650208},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.7250000238418579},{"id":"https://openalex.org/keywords/attentional-gating","display_name":"attentional gating","score":0.597000002861023},{"id":"https://openalex.org/keywords/expert-pruning","display_name":"expert pruning","score":0.8650000095367432},{"id":"https://openalex.org/keywords/architectural-diversity","display_name":"architectural diversity","score":0.6610000133514404},{"id":"https://openalex.org/keywords/node-classification","display_name":"node classification","score":0.6190000176429749},{"id":"https://openalex.org/keywords/graph-classification","display_name":"graph classification","score":0.9919999837875366},{"id":"https://openalex.org/keywords/link-prediction","display_name":"link prediction","score":0.9139999747276306},{"id":"https://openalex.org/keywords/graph-regression","display_name":"graph regression","score":0.7110000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831000089645386},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5814999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507000088691711},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26600000262260437}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2511.13062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.13062","pdf_url":"https://arxiv.org/pdf/2511.13062","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/39615","doi":null,"is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39615","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39615/43576","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2511.13062","doi":"https://doi.org/10.48550/arxiv.2511.13062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.13062","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,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.13062","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.13062","pdf_url":"https://arxiv.org/pdf/2511.13062","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0,83],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,17],"emerged":[5],"as":[6,33],"powerful":[7],"tools":[8],"for":[9,70,232],"learning":[10],"over":[11],"graph-structured":[12],"data,":[13],"yet":[14],"recent":[15],"studies":[16],"shown":[18],"that":[19,93,115,157,213],"their":[20],"performance":[21,46],"gains":[22],"are":[23,181,192],"beginning":[24],"to":[25,95,134,138],"plateau.":[26],"In":[27],"many":[28],"cases,":[29],"well-established":[30],"models":[31,104,180],"such":[32],"GCN":[34],"and":[35,90,98,128,166,183,185,189,207,211,222,229],"GAT,":[36],"when":[37],"appropriately":[38],"tuned,":[39],"can":[40],"match":[41],"or":[42,75,217],"even":[43],"exceed":[44],"the":[45,59,62,66,100,143,146,159,187],"of":[47,64,85,109,119,145,161],"more":[48],"complex,":[49],"state-of-the-art":[50],"architectures.":[51,110],"This":[52],"trend":[53],"highlights":[54],"a":[55,71,88,106,120,129,154,174,227],"key":[56],"limitation":[57],"in":[58,177],"current":[60],"landscape:":[61],"difficulty":[63],"selecting":[65],"most":[67,101],"suitable":[68],"model":[69],"given":[72],"graph":[73,204,234],"task":[74],"dataset.":[76],"To":[77,149],"address":[78],"this,":[79],"we":[80],"propose":[81],"Self-Adaptive":[82],"Mixture":[84],"Models":[86],"(SAGMM),":[87],"modular":[89],"practical":[91],"framework":[92],"learns":[94],"automatically":[96],"select":[97],"combine":[99],"appropriate":[102],"GNN":[103,220],"from":[105],"diverse":[107],"pool":[108],"Unlike":[111],"prior":[112,223],"mixture-of-experts":[113],"approaches":[114],"rely":[116],"on":[117,142,197],"variations":[118],"single":[121],"base":[122],"model,":[123],"SAGMM":[124,152,196],"leverages":[125],"architectural":[126],"diversity":[127],"topology-aware":[130],"attention":[131],"gating":[132,188],"mechanism":[133,156],"adaptively":[135],"assign":[136],"experts":[137,163],"each":[139],"node":[140,202],"based":[141],"structure":[144],"input":[147],"graph.":[148],"improve":[150],"efficiency,":[151],"includes":[153],"pruning":[155],"reduces":[158],"number":[160],"active":[162],"during":[164],"training":[165],"inference":[167],"without":[168],"compromising":[169],"performance.":[170],"We":[171,194],"also":[172],"explore":[173],"training-efficient":[175],"variant":[176],"which":[178],"expert":[179],"pretrained":[182],"frozen,":[184],"only":[186],"task-specific":[190],"layers":[191],"trained.":[193],"evaluate":[195],"16":[198],"benchmark":[199],"datasets":[200],"covering":[201],"classification,":[203,205],"regression,":[206],"link":[208],"prediction":[209],"tasks,":[210],"demonstrate":[212],"it":[214],"consistently":[215],"outperforms":[216],"matches":[218],"leading":[219],"baselines":[221],"mixture-based":[224],"methods,":[225],"offering":[226],"robust":[228],"adaptive":[230],"solution":[231],"real-world":[233],"learning.":[235]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-11-19T00:00:00"}