{"id":"https://openalex.org/W4409150166","doi":"https://doi.org/10.1145/3690624.3709292","title":"Lorentzian Residual Neural Networks","display_name":"Lorentzian Residual Neural Networks","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409150166","doi":"https://doi.org/10.1145/3690624.3709292"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709292","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3690624.3709292","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011028689","display_name":"Neil He","orcid":null},"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":"Neil He","raw_affiliation_strings":["Yale University, New Haven, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, Connecticut, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","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":false,"raw_author_name":"Menglin Yang","raw_affiliation_strings":["Yale University, New Haven, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, Connecticut, USA","institution_ids":["https://openalex.org/I32971472"]}]},{"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, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"Yale University, New Haven, Connecticut, USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011028689"],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90171897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9901999831199646,"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/T10320","display_name":"Neural Networks and Applications","score":0.9901999831199646,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9789999723434448,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9739999771118164,"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/residual","display_name":"Residual","score":0.7263084650039673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.609565019607544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6094242930412292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32282593846321106},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1934751570224762}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7263084650039673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.609565019607544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6094242930412292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32282593846321106},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1934751570224762}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709292","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3690624.3709292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709292","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1971215074","https://openalex.org/W2030407863","https://openalex.org/W2088962804","https://openalex.org/W2194775991","https://openalex.org/W2400540722","https://openalex.org/W3035102141","https://openalex.org/W3164410012","https://openalex.org/W3177564060","https://openalex.org/W3187395669","https://openalex.org/W4253449023","https://openalex.org/W4312533318","https://openalex.org/W4390872537","https://openalex.org/W6600195515","https://openalex.org/W6601691205"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2560215812","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2949601986"],"abstract_inverted_index":{"Hyperbolic":[0],"neural":[1,38,81,108,168],"networks":[2,47,109,169],"have":[3,30],"emerged":[4],"as":[5,52,174],"a":[6,77,175],"powerful":[7],"tool":[8],"for":[9,43,164],"modeling":[10],"hierarchical":[11,113],"data":[12],"structures":[13],"prevalent":[14],"in":[15,33,89,105,170],"real-world":[16],"datasets.":[17],"Notably,":[18],"residual":[19,46,80,103],"connections,":[20],"which":[21],"facilitate":[22],"the":[23,34,67,85,90,99,142,160],"direct":[24],"flow":[25],"of":[26,36,93,102,147,162],"information":[27],"across":[28],"layers,":[29],"been":[31],"instrumental":[32],"success":[35],"deep":[37],"networks.":[39],"However,":[40],"current":[41],"methods":[42,125],"constructing":[44],"hyperbolic":[45,94,107,155,171],"suffer":[48],"from":[49,66],"limitations":[50],"such":[51],"increased":[53],"model":[54,92],"complexity,":[55],"numerical":[56],"instability,":[57],"and":[58,65,131,138,145,154,185],"errors":[59],"due":[60],"to":[61,64,151,179],"multiple":[62,180],"mappings":[63],"tangent":[68],"space.":[69],"To":[70],"address":[71],"these":[72],"limitations,":[73],"we":[74],"introduce":[75],"LResNet,":[76],"novel":[78],"Lorentzian":[79,87],"network":[82],"based":[83],"on":[84,135],"weighted":[86],"centroid":[88],"Lorentz":[91,106],"geometry.":[95],"Our":[96,157],"method":[97,120,149,178],"enables":[98],"efficient":[100],"integration":[101],"connections":[104],"while":[110,126],"preserving":[111],"their":[112],"representation":[114],"capabilities.":[115],"We":[116],"demonstrate":[117],"that":[118],"our":[119,148],"can":[121],"theoretically":[122],"derive":[123],"previous":[124],"offering":[127],"improved":[128],"stability,":[129],"efficiency,":[130],"effectiveness.":[132],"Extensive":[133],"experiments":[134],"both":[136],"graph":[137,186],"vision":[139],"tasks":[140],"showcase":[141],"superior":[143],"performance":[144],"robustness":[146],"compared":[150],"state-of-the-art":[152],"Euclidean":[153],"alternatives.":[156],"findings":[158],"highlight":[159],"potential":[161],"LResNet":[163],"building":[165],"more":[166],"expressive":[167],"embedding":[172],"space":[173],"generally":[176],"applicable":[177],"architectures,":[181],"including":[182],"CNNs,":[183],"GNNs,":[184],"Transformers.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}