{"id":"https://openalex.org/W4401857077","doi":"https://doi.org/10.1145/3637528.3672039","title":"Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space","display_name":"Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857077","doi":"https://doi.org/10.1145/3637528.3672039"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3672039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3672039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091585620","display_name":"Meng\u2010Lin Yang","orcid":"https://orcid.org/0000-0003-2510-5282"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Menglin Yang","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108973979","display_name":"Harshit Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshit Verma","raw_affiliation_strings":["Birla Institute of Technology and Science, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science, Hyderabad, India","institution_ids":["https://openalex.org/I4210101034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034752587","display_name":"Delvin Ce Zhang","orcid":"https://orcid.org/0000-0001-5571-9766"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Delvin Ce Zhang","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103463206","display_name":"Jiahong Liu","orcid":"https://orcid.org/0000-0002-8551-120X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahong Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042251906","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Irwin King","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078337825","display_name":"Rex Ying","orcid":"https://orcid.org/0000-0002-5856-5229"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rex Ying","raw_affiliation_strings":["Yale University, New Haven, CT, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, CT, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091585620"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":4.5177,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95226137,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3770","last_page":"3781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9980000257492065,"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":0.9980000257492065,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9855999946594238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6034289598464966},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5507326722145081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4932824969291687},{"id":"https://openalex.org/keywords/hyperbolic-tree","display_name":"Hyperbolic tree","score":0.48212289810180664},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4158984124660492},{"id":"https://openalex.org/keywords/hyperbolic-manifold","display_name":"Hyperbolic manifold","score":0.40454375743865967},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3991340100765228},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36687546968460083},{"id":"https://openalex.org/keywords/hyperbolic-function","display_name":"Hyperbolic function","score":0.3553348183631897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30543529987335205},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.220778226852417},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.20793628692626953},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.2047336995601654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15510210394859314},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11846330761909485}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6034289598464966},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5507326722145081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4932824969291687},{"id":"https://openalex.org/C97654310","wikidata":"https://www.wikidata.org/wiki/Q574023","display_name":"Hyperbolic tree","level":4,"score":0.48212289810180664},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4158984124660492},{"id":"https://openalex.org/C70984080","wikidata":"https://www.wikidata.org/wiki/Q2619102","display_name":"Hyperbolic manifold","level":3,"score":0.40454375743865967},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3991340100765228},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36687546968460083},{"id":"https://openalex.org/C92047909","wikidata":"https://www.wikidata.org/wiki/Q204034","display_name":"Hyperbolic function","level":2,"score":0.3553348183631897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30543529987335205},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.220778226852417},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.20793628692626953},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.2047336995601654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15510210394859314},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11846330761909485},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3672039","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3672039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1971215074","https://openalex.org/W2003240077","https://openalex.org/W2519536754","https://openalex.org/W2892880750","https://openalex.org/W2982490267","https://openalex.org/W2997136781","https://openalex.org/W3021975806","https://openalex.org/W3035102141","https://openalex.org/W3035134435","https://openalex.org/W3036106327","https://openalex.org/W3038054432","https://openalex.org/W3100078588","https://openalex.org/W3127180058","https://openalex.org/W3131922516","https://openalex.org/W3163629447","https://openalex.org/W3167985505","https://openalex.org/W3171364227","https://openalex.org/W3177564060","https://openalex.org/W3187395669","https://openalex.org/W3201579042","https://openalex.org/W3209692422","https://openalex.org/W3210423603","https://openalex.org/W3212655958","https://openalex.org/W4206865191","https://openalex.org/W4224313222","https://openalex.org/W4225097908","https://openalex.org/W4226208698","https://openalex.org/W4231418571","https://openalex.org/W4253449023","https://openalex.org/W4281706128","https://openalex.org/W4284896159","https://openalex.org/W4287122949","https://openalex.org/W4287558099","https://openalex.org/W4287775237","https://openalex.org/W4290874888","https://openalex.org/W4292779060","https://openalex.org/W4312533318","https://openalex.org/W4380993339","https://openalex.org/W4385568389","https://openalex.org/W4385568419","https://openalex.org/W4385696031","https://openalex.org/W4393159312","https://openalex.org/W4396843991","https://openalex.org/W6767121309","https://openalex.org/W6778883912","https://openalex.org/W6839395506"],"related_works":["https://openalex.org/W2969261150","https://openalex.org/W4384937846","https://openalex.org/W1541587918","https://openalex.org/W3191635729","https://openalex.org/W2218000531","https://openalex.org/W1513263832","https://openalex.org/W4256533437","https://openalex.org/W2952691602","https://openalex.org/W2950238559","https://openalex.org/W1585146582"],"abstract_inverted_index":{"Hyperbolic":[0],"geometry":[1],"have":[2,43,56],"shown":[3],"significant":[4],"potential":[5,187],"in":[6,50,75,144,154],"modeling":[7],"complex":[8],"structured":[9],"data,":[10],"particularly":[11],"those":[12],"with":[13],"underlying":[14],"tree-like":[15],"and":[16,165,178,191,198],"hierarchical":[17],"structures.":[18],"Despite":[19],"the":[20,34,51,70,90,95,101,123,138,142,169,176],"impressive":[21],"performance":[22],"of":[23,59,72,94,103,126,141,180],"various":[24,183],"hyperbolic":[25,37,63,76,97,119,127,145,155,158],"neural":[26],"networks":[27],"across":[28,182],"numerous":[29],"domains,":[30],"research":[31],"on":[32,46,122],"adapting":[33],"Transformer":[35,120,143,159],"to":[36,160],"space":[38],"remains":[39],"limited.":[40],"Previous":[41],"attempts":[42],"mainly":[44],"focused":[45],"modifying":[47],"self-attention":[48,98,152],"modules":[49,74,140],"Transformer.":[52,64],"However,":[53],"these":[54,112],"efforts":[55],"fallen":[57],"short":[58],"developing":[60],"a":[61,117,150],"complete":[62],"This":[65],"stems":[66],"primarily":[67],"from:":[68],"(i)":[69],"absence":[71],"well-defined":[73],"space,":[77,156],"including":[78],"linear":[79,151],"transformation":[80],"layers,":[81,83],"LayerNorm":[82],"activation":[84],"functions,":[85],"dropout":[86],"operations,":[87],"etc.":[88],"(ii)":[89],"quadratic":[91],"time":[92],"complexity":[93],"existing":[96],"module":[99],"w.r.t":[100],"number":[102],"input":[104],"tokens,":[105],"which":[106],"hinders":[107],"its":[108,186],"scalability.":[109],"To":[110],"address":[111],"challenges,":[113],"we":[114,131,148],"propose,":[115],"Hypformer,":[116,130],"novel":[118],"based":[121],"Lorentz":[124],"model":[125],"geometry.":[128],"In":[129],"introduce":[132],"two":[133],"foundational":[134],"blocks":[135],"that":[136],"define":[137],"essential":[139],"space.":[146],"Furthermore,":[147],"develop":[149],"mechanism":[153],"enabling":[157],"process":[161],"billion-scale":[162],"graph":[163],"data":[164,196],"long-sequence":[166],"inputs":[167],"for":[168,194],"first":[170],"time.":[171],"Our":[172],"experimental":[173],"results":[174],"confirm":[175],"effectiveness":[177],"efficiency":[179],"\\method":[181],"datasets,":[184],"demonstrating":[185],"as":[188],"an":[189],"effective":[190],"scalable":[192],"solution":[193],"large-scale":[195],"representation":[197],"large":[199],"models.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}