{"id":"https://openalex.org/W7161111648","doi":"https://doi.org/10.48550/arxiv.2605.13690","title":"The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks","display_name":"The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161111648","doi":"https://doi.org/10.48550/arxiv.2605.13690"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13690","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.13690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102188823","display_name":"Fengqing Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Fengqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136177247","display_name":"Yuetai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuetai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136108361","display_name":"Yichen Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136124914","display_name":"Kaiyuan Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Kaiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018806127","display_name":"Luyao Niu","orcid":"https://orcid.org/0000-0001-8591-5522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Luyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052064870","display_name":"Bhaskar Ramasubramanian","orcid":"https://orcid.org/0000-0002-2166-7838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramasubramanian, Bhaskar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019524943","display_name":"Basel Alomair","orcid":"https://orcid.org/0000-0002-0494-2586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alomair, Basel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136176016","display_name":"Linda Bushnell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bushnell, Linda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079723268","display_name":"Radha Poovendran","orcid":"https://orcid.org/0000-0003-0269-8097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poovendran, Radha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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":0.9496999979019165,"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":0.9496999979019165,"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":0.007000000216066837,"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":0.00570000009611249,"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/hypergraph","display_name":"Hypergraph","score":0.8185999989509583},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.4867999851703644},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.46059998869895935},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.427700012922287},{"id":"https://openalex.org/keywords/homomorphism","display_name":"Homomorphism","score":0.41839998960494995},{"id":"https://openalex.org/keywords/clique","display_name":"Clique","score":0.4162999987602234},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.3785000145435333},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.36239999532699585}],"concepts":[{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.8185999989509583},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.6276999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5231999754905701},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C2777035058","wikidata":"https://www.wikidata.org/wiki/Q1662634","display_name":"Clique","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.375900000333786},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C97654310","wikidata":"https://www.wikidata.org/wiki/Q574023","display_name":"Hyperbolic tree","level":4,"score":0.3402000069618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C128896722","wikidata":"https://www.wikidata.org/wiki/Q1501387","display_name":"Transitive closure","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C136979486","wikidata":"https://www.wikidata.org/wiki/Q773483","display_name":"Existential quantification","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13690","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":"doi:10.48550/arxiv.2605.13690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13690","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":"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":{"Hypergraphs":[0],"provide":[1],"a":[2,63,68,91,100,103,126],"natural":[3],"framework":[4,124],"to":[5,20],"model":[6],"higher-order":[7,30],"interactions":[8],"in":[9,67],"scientific,":[10],"social,":[11],"and":[12,51,87,140,174],"biological":[13],"systems.":[14],"Hypergraph":[15],"neural":[16],"networks":[17],"(HGNNs)":[18],"aim":[19],"learn":[21],"from":[22],"such":[23],"data,":[24],"yet":[25],"it":[26],"remains":[27],"unclear":[28],"which":[29,44,59,108],"structures":[31],"these":[32],"models":[33,143],"can":[34,49,117],"represent.":[35],"We":[36,53,151],"show":[37,78],"that":[38,79,144],"hypergraph":[39,85],"expressivity":[40,146],"is":[41],"governed":[42],"by":[43,95,137],"small":[45],"patterns":[46],"an":[47,157],"architecture":[48],"detect":[50],"count.":[52],"formalize":[54],"this":[55,154],"via":[56],"homomorphism":[57,80],"densities,":[58],"measure":[60],"how":[61],"often":[62],"structural":[64],"motif":[65],"appears":[66],"hypergraph.":[69],"Combining":[70],"classical":[71],"homomorphism-count":[72],"completeness":[73],"with":[74],"invariant":[75],"approximation,":[76],"we":[77],"densities":[81],"generate":[82],"all":[83],"continuous":[84],"invariants":[86,119],"organize":[88],"them":[89],"into":[90],"strict":[92],"hierarchy":[93],"indexed":[94],"hypertree":[96],"width.":[97],"This":[98],"yields":[99],"Width":[101,167],"Wall:":[102],"fundamental":[104],"architectural":[105],"limit":[106],"beyond":[107,147],"no":[109],"hidden":[110],"dimension,":[111],"training":[112],"procedure":[113],"or":[114],"fixed-depth":[115],"HGNN":[116,131],"represent":[118],"requiring":[120],"wider":[121],"patterns.":[122],"Our":[123],"provides":[125],"unified":[127],"characterization":[128],"of":[129,162],"15":[130],"architectures,":[132],"precisely":[133],"identifies":[134],"information":[135],"lost":[136],"clique":[138],"expansion,":[139],"motivates":[141],"density-aware":[142],"extend":[145],"bounded-width":[148],"message":[149],"passing.":[150],"experimentally":[152],"validate":[153],"finding":[155],"on":[156],"APPLICATION":[158],"NODE":[159],"CLASSIFICATION":[160],"SUITE":[161],"real-world":[163],"hypergraphs,":[164],"where":[165],"the":[166],"Wall":[168],"predicts":[169],"when":[170,175],"graph-reduction":[171],"baselines":[172],"fail":[173],"density":[176],"features":[177],"help.":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}