{"id":"https://openalex.org/W7128546565","doi":"https://doi.org/10.48550/arxiv.2602.08431","title":"USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation","display_name":"USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128546565","doi":"https://doi.org/10.48550/arxiv.2602.08431"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.08431","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125562159","display_name":"Yingxu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yingxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125548974","display_name":"Kunyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kunyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125482231","display_name":"Mengzhu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Mengzhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125538619","display_name":"Siyang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Siyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125527445","display_name":"Nan Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.9506000280380249,"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":0.9506000280380249,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.031099999323487282,"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":0.002099999925121665,"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/basis","display_name":"Basis (linear algebra)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4828999936580658},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3919999897480011},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3896999955177307},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.384799987077713},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.3799000084400177},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3650999963283539},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.3278000056743622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049000263214111},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.384799987077713},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.08431","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.08431","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08431","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.08431","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"SF-GDA":[0],"is":[1,108],"pivotal":[2],"for":[3,92],"privacy-preserving":[4],"knowledge":[5],"transfer":[6],"across":[7],"graph":[8],"datasets.":[9],"Although":[10],"recent":[11],"works":[12],"incorporate":[13],"structural":[14,90,139,182,231],"information,":[15],"they":[16],"implicitly":[17],"condition":[18],"adaptation":[19,62,241],"on":[20,207,217],"the":[21,46,55,70,79,117,133,143,147,152,171,176,202,208,212,240,244],"smoothness":[22],"priors":[23],"of":[24,95,120,185,211],"sourcetrained":[25],"GNNs,":[26],"thereby":[27],"limiting":[28],"their":[29],"generalization":[30],"to":[31,86,101,109,131,145,164],"structurally":[32],"distinct":[33,50],"targets.":[34],"This":[35,173],"dependency":[36],"becomes":[37],"a":[38,75,83,88,97,102,111,127,137,180,195],"critical":[39],"bottleneck":[40],"under":[41],"significant":[42],"topological":[43,51,122,158],"shifts,":[44,232],"where":[45],"source":[47,56,99,134],"model":[48,85,100],"misinterprets":[49],"patterns":[52],"unseen":[53],"in":[54,170,227],"domain":[57],"as":[58],"noise,":[59],"rendering":[60],"pseudo-label-based":[61],"unreliable.":[63],"To":[64],"overcome":[65],"this":[66],"limitation,":[67],"we":[68,193],"propose":[69],"Universal":[71],"Structural":[72],"Basis":[73],"Distillation,":[74],"framework":[76,130],"that":[77,114,175,199,220],"shifts":[78],"paradigm":[80],"from":[81,161,243],"adapting":[82,96],"biased":[84,98],"learning":[87],"universal":[89],"basis":[91,113,154,178],"SF-GDA.":[93],"Instead":[94],"specific":[103],"target,":[104],"our":[105],"core":[106],"idea":[107],"construct":[110],"structure-agnostic":[112],"proactively":[115],"covers":[116],"full":[118,148],"spectrum":[119],"potential":[121],"patterns.":[123],"Specifically,":[124],"USBD":[125,221],"employs":[126],"bi-level":[128],"optimization":[129],"distill":[132],"dataset":[135],"into":[136],"compact":[138],"basis.":[140],"By":[141],"enforcing":[142],"prototypes":[144],"span":[146],"Dirichlet":[149],"energy":[150],"spectrum,":[151],"learned":[153,177],"explicitly":[155],"captures":[156],"diverse":[157],"motifs,":[159],"ranging":[160],"low-frequency":[162],"clusters":[163],"high-frequency":[165],"chains,":[166],"beyond":[167],"those":[168],"present":[169],"source.":[172],"ensures":[174],"creates":[179],"comprehensive":[181],"covering":[183],"capable":[184],"handling":[186],"targets":[187],"with":[188,229],"disparate":[189],"structures.":[190],"For":[191],"inference,":[192],"introduce":[194],"spectral-aware":[196],"ensemble":[197],"mechanism":[198],"dynamically":[200],"activates":[201],"optimal":[203],"prototype":[204],"combination":[205],"based":[206],"spectral":[209],"fingerprint":[210],"target":[213,245],"graph.":[214],"Extensive":[215],"experiments":[216],"benchmarks":[218],"demonstrate":[219],"significantly":[222],"outperforms":[223],"state-of-the-art":[224],"methods,":[225],"particularly":[226],"scenarios":[228],"severe":[230],"while":[233],"achieving":[234],"superior":[235],"computational":[236],"efficiency":[237],"by":[238],"decoupling":[239],"cost":[242],"data":[246],"scale.":[247]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-11T00:00:00"}