{"id":"https://openalex.org/W7154251130","doi":"https://doi.org/10.48550/arxiv.2604.10955","title":"Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing","display_name":"Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154251130","doi":"https://doi.org/10.48550/arxiv.2604.10955"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10955","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,"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":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.2604.10955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133552902","display_name":"Zhiheng Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130212872","display_name":"Mengyao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Mengyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641900","display_name":"Xixun Lin","orcid":"https://orcid.org/0009-0004-6645-0597"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xixun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133577552","display_name":"Xingqin Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Xingqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129842200","display_name":"Guiying Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Guiying","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":0.9236999750137329,"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":0.9236999750137329,"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/T12303","display_name":"Tensor decomposition and applications","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12536","display_name":"Topological and Geometric Data Analysis","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/hypergraph","display_name":"Hypergraph","score":0.885200023651123},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5587999820709229},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.555400013923645},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.453900009393692},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3982999920845032},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38510000705718994},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.38109999895095825}],"concepts":[{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.885200023651123},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40869998931884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4058000147342682},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.3021000027656555},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2711000144481659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10955","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,"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":"doi:10.48550/arxiv.2604.10955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10955","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Hypergraph":[0,41],"neural":[1,54,122],"networks":[2],"(HGNNs)":[3],"have":[4],"shown":[5],"remarkable":[6],"potential":[7],"in":[8,15,62,205],"modeling":[9],"high-order":[10],"relationships":[11],"that":[12,48,130,192],"naturally":[13],"arise":[14],"many":[16],"real-world":[17],"data":[18],"domains.":[19],"However,":[20],"existing":[21],"HGNNs":[22],"often":[23],"suffer":[24],"from":[25],"shallow":[26],"propagation,":[27],"oversmoothing,":[28],"and":[29,72,75,115,152,156,174,183,210],"limited":[30],"adaptability":[31],"to":[32],"complex":[33],"hypergraph":[34,65,70,99,213],"structures.":[35],"In":[36],"this":[37,120],"paper,":[38],"we":[39],"propose":[40],"Neural":[42],"Diffusion":[43],"(HND),":[44],"a":[45,63,78,94,126,133,148,164],"novel":[46],"framework":[47,162],"unifies":[49],"nonlinear":[50],"diffusion":[51,66,109,117,134],"equations":[52],"with":[53],"message":[55,123],"passing":[56,124],"on":[57,188],"hypergraphs.":[58],"HND":[59,161,193],"is":[60,104],"grounded":[61],"continuous-time":[64],"equation,":[67],"formulated":[68],"via":[69,147],"gradient":[71,128],"divergence":[73],"operators,":[74],"modulated":[76],"by":[77,112],"learnable,":[79],"structure-aware":[80],"coefficient":[81],"matrix":[82],"over":[83],"hyperedge-node":[84],"pairs.":[85],"This":[86],"partial":[87],"differential":[88],"equation":[89],"(PDE)":[90],"based":[91],"formulation":[92],"provides":[93],"physically":[95],"interpretable":[96,184],"view":[97],"of":[98,166,180,202,212],"learning,":[100],"where":[101],"feature":[102],"propagation":[103],"understood":[105],"as":[106,170],"an":[107],"anisotropic":[108],"process":[110],"governed":[111],"local":[113],"inconsistency":[114],"adaptive":[116],"coefficient.":[118],"From":[119],"perspective,":[121],"becomes":[125],"discretized":[127],"flow":[129],"progressively":[131],"minimizes":[132],"energy":[135,143],"functional.":[136],"We":[137],"derive":[138],"rigorous":[139],"theoretical":[140],"guarantees,":[141],"including":[142],"dissipation,":[144],"solution":[145],"boundedness":[146],"discrete":[149],"maximum":[150],"principle,":[151],"stability":[153],"under":[154],"explicit":[155],"implicit":[157],"numerical":[158],"schemes.":[159],"The":[160],"supports":[163],"variety":[165],"integration":[167],"strategies":[168],"such":[169],"non-adaptive-step":[171],"(like":[172],"Runge-Kutta)":[173],"adaptive-step":[175],"solvers,":[176],"enabling":[177],"the":[178,200,207],"construction":[179],"deep,":[181],"stable,":[182],"architectures.":[185],"Extensive":[186],"experiments":[187],"benchmark":[189],"datasets":[190],"demonstrate":[191],"achieves":[194],"competitive":[195],"performance.":[196],"Our":[197],"results":[198],"highlight":[199],"power":[201],"PDE-inspired":[203],"design":[204],"enhancing":[206],"stability,":[208],"expressivity,":[209],"interpretability":[211],"learning.":[214]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-15T00:00:00"}