{"id":"https://openalex.org/W7160611362","doi":"https://doi.org/10.48550/arxiv.2605.05759","title":"Full-Spectrum Graph Neural Networks: Expressive and Scalable","display_name":"Full-Spectrum Graph Neural Networks: Expressive and Scalable","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160611362","doi":"https://doi.org/10.48550/arxiv.2605.05759"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05759","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05759","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":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.2605.05759","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135677063","display_name":"Xiaohan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028066599","display_name":"Deyu Bo","orcid":"https://orcid.org/0000-0003-2063-8223"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo, Deyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135682317","display_name":"Longlong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Longlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135694717","display_name":"Kelin Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Kelin","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":0.9929999709129333,"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":0.9929999709129333,"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":0.0010000000474974513,"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":0.0008999999845400453,"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/bounded-function","display_name":"Bounded function","score":0.5999000072479248},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5127000212669373},{"id":"https://openalex.org/keywords/expressive-power","display_name":"Expressive power","score":0.4754999876022339},{"id":"https://openalex.org/keywords/universality","display_name":"Universality (dynamical systems)","score":0.46889999508857727},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.427700012922287},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.42170000076293945},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4036000072956085}],"concepts":[{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5353000164031982},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C183992945","wikidata":"https://www.wikidata.org/wiki/Q2495574","display_name":"Universality (dynamical systems)","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42489999532699585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3864000141620636},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C74003402","wikidata":"https://www.wikidata.org/wiki/Q3180727","display_name":"Spectral graph theory","level":5,"score":0.33709999918937683},{"id":"https://openalex.org/C187455244","wikidata":"https://www.wikidata.org/wiki/Q942353","display_name":"Boolean function","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C201943243","wikidata":"https://www.wikidata.org/wiki/Q7551008","display_name":"Social connectedness","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C64341305","wikidata":"https://www.wikidata.org/wiki/Q4919225","display_name":"Bivariate analysis","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05759","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05759","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05759","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05759","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"It":[0],"is":[1,27],"well":[2],"established":[3],"that":[4,93,107,137,147],"spectral":[5,53,57,80,95,156],"graph":[6,130],"neural":[7],"networks":[8],"(GNNs)":[9],"can":[10,109],"universally":[11,119],"approximate":[12],"node":[13,68],"signals;":[14],"however,":[15],"their":[16,30],"expressive":[17,114],"power":[18],"remains":[19],"bounded":[20],"by":[21],"the":[22,44,67,71,78,123,167],"1-dimensional":[23],"Weisfeiler-Lehman":[24],"test,":[25],"which":[26],"mirrored":[28],"in":[29],"lack":[31],"of":[32,51,103,154],"universality":[33],"for":[34,128],"higher-order":[35],"signals.":[36],"To":[37],"go":[38],"beyond":[39],"this":[40],"bound,":[41],"we":[42],"propose":[43],"Full-Spectrum":[45],"GNNs":[46,96],"(FSpecGNNs),":[47],"a":[48,85,99,144,152],"second-order":[49],"generalization":[50],"classical":[52,94],"GNNs.":[54],"FSpecGNN":[55,133,165],"advances":[56],"filtering":[58],"from":[59,66],"two":[60],"perspectives:":[61],"(1)":[62],"it":[63,76,158],"lifts":[64],"signals":[65],"domain":[69],"to":[70,84,151],"node-pair":[72,121],"domain;":[73],"and":[74,105,170],"(2)":[75],"extends":[77],"univariate":[79],"filter":[81,87],"over":[82,88],"eigenvalues":[83],"bivariate":[86],"eigenvalue":[89],"pairs.":[90],"We":[91],"show":[92],"arise":[97],"as":[98,113,115],"diagonal":[100],"special":[101],"case":[102],"FSpecGNNs,":[104],"prove":[106],"FSpecGNNs":[108],"be":[110],"at":[111],"most":[112],"Local":[116],"2-GNN":[117],"while":[118],"approximating":[120],"signals,":[122],"latter":[124],"being":[125],"particularly":[126],"beneficial":[127],"heterophilic":[129,175],"learning.":[131],"Moreover,":[132],"admits":[134],"scalable":[135],"implementations":[136],"avoid":[138],"explicit":[139],"node-pair-level":[140],"computations;":[141],"combined":[142],"with":[143],"low-rank":[145],"approximation":[146],"reduces":[148],"full-spectrum":[149],"convolution":[150],"combination":[153],"polynomial":[155],"filters,":[157],"enables":[159],"learning":[160],"on":[161,174],"large":[162],"graphs.":[163],"Empirically,":[164],"validates":[166],"predicted":[168],"expressivity":[169],"delivers":[171],"strong":[172],"performance":[173],"benchmarks.":[176]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}