{"id":"https://openalex.org/W4385568313","doi":"https://doi.org/10.1145/3580305.3599338","title":"Exploiting Relation-aware Attribute Representation Learning in Knowledge Graph Embedding for Numerical Reasoning","display_name":"Exploiting Relation-aware Attribute Representation Learning in Knowledge Graph Embedding for Numerical Reasoning","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385568313","doi":"https://doi.org/10.1145/3580305.3599338"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599338","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066332706","display_name":"Gayeong Kim","orcid":"https://orcid.org/0009-0004-5193-7722"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gayeong Kim","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-5193-7722","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906220","display_name":"Sookyung Kim","orcid":"https://orcid.org/0009-0005-2697-1053"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sookyung Kim","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-2697-1053","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053055523","display_name":"Ko Keun Kim","orcid":"https://orcid.org/0000-0001-7511-4326"},"institutions":[{"id":"https://openalex.org/I4210131320","display_name":"LG (South Korea)","ror":"https://ror.org/03ddh2c27","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ko Keun Kim","raw_affiliation_strings":["LG Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7511-4326","affiliations":[{"raw_affiliation_string":"LG Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210131320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086572288","display_name":"Suchan Park","orcid":"https://orcid.org/0009-0008-9320-3195"},"institutions":[{"id":"https://openalex.org/I4210131320","display_name":"LG (South Korea)","ror":"https://ror.org/03ddh2c27","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210131320"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suchan Park","raw_affiliation_strings":["LG Electronics, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-9320-3195","affiliations":[{"raw_affiliation_string":"LG Electronics, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210131320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102788513","display_name":"Heesoo Jung","orcid":"https://orcid.org/0000-0002-6554-2391"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heesoo Jung","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6554-2391","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071646906","display_name":"Hogun Park","orcid":"https://orcid.org/0000-0003-0576-5806"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hogun Park","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0576-5806","affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8691,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7424223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9944000244140625,"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/T11719","display_name":"Data Quality and Management","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7788828015327454},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7302297353744507},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6559005975723267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5492874383926392},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5384243726730347},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5092970132827759},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5025458335876465},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49896883964538574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49417999386787415},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4781726002693176},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.43618786334991455},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.426434725522995},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3401893079280853},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.31675654649734497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788828015327454},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7302297353744507},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6559005975723267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5492874383926392},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5384243726730347},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5092970132827759},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5025458335876465},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49896883964538574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49417999386787415},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4781726002693176},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.43618786334991455},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.426434725522995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3401893079280853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31675654649734497},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3580305.3599338","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599338","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599338","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385568313.pdf","grobid_xml":"https://content.openalex.org/works/W4385568313.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2016753842","https://openalex.org/W2085988980","https://openalex.org/W2127795553","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2250184916","https://openalex.org/W2283196293","https://openalex.org/W2728059831","https://openalex.org/W2885483808","https://openalex.org/W2898085636","https://openalex.org/W2914592219","https://openalex.org/W2950393809","https://openalex.org/W2964161331","https://openalex.org/W2980763157","https://openalex.org/W2997897037","https://openalex.org/W3035134435","https://openalex.org/W3095602948","https://openalex.org/W3101704389","https://openalex.org/W3103296573","https://openalex.org/W3117298090","https://openalex.org/W3156968278","https://openalex.org/W3164006073","https://openalex.org/W3171874185","https://openalex.org/W3172710079","https://openalex.org/W3199807247","https://openalex.org/W3210423603","https://openalex.org/W3212655958","https://openalex.org/W4221160815","https://openalex.org/W4283688275","https://openalex.org/W4294170691","https://openalex.org/W6745136726","https://openalex.org/W6784694379"],"related_works":["https://openalex.org/W2604454537","https://openalex.org/W2808284704","https://openalex.org/W2897702399","https://openalex.org/W4206028705","https://openalex.org/W2237537322","https://openalex.org/W2757431232","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2954554213","https://openalex.org/W2251363251"],"abstract_inverted_index":{"Numerical":[0],"reasoning":[1,18,98],"is":[2,30,71,189],"an":[3,45,167],"essential":[4],"task":[5,19],"for":[6,96],"supporting":[7],"machine":[8],"learning":[9,111,132],"applications,":[10],"such":[11],"as":[12],"recommendation":[13],"and":[14,25,38,120,138,175],"information":[15,37],"retrieval.":[16],"The":[17],"aims":[20],"to":[21,63,134,171,177,182],"compare":[22],"two":[23],"items":[24],"infer":[26],"new":[27],"facts":[28],"(e.g.,":[29,41],"taller":[31],"than)":[32],"by":[33],"leveraging":[34,56],"existing":[35,52],"relational":[36],"numerical":[39,65,97,123,148],"attributes":[40,78,149],"the":[42,68,116,154,183],"height":[43],"of":[44,156,169],"entity)":[46],"in":[47,75,173,179],"knowledge":[48],"graphs.":[49],"However,":[50],"most":[51],"methods":[53],"rely":[54],"on":[55],"attribute":[57,89,109],"encoders":[58],"or":[59],"additional":[60],"loss":[61],"functions":[62],"predict":[64],"relations.":[66],"Therefore,":[67],"prediction":[69],"performance":[70],"often":[72],"not":[73],"robust":[74,130],"cases":[76],"when":[77,147],"are":[79,150],"sparsely":[80,151],"observed.":[81],"In":[82,125,153],"this":[83],"paper,":[84],"we":[85,101,127],"propose":[86],"a":[87,106,129],"Relation-AAware":[88],"representation":[90,110],"learning-based":[91],"Knowledge":[92],"Graph":[93],"Embedding":[94],"method":[95,133],"tasks,":[99],"which":[100,113],"call":[102],"RAKGE.":[103],"RAKGE":[104],"incorporates":[105],"newly":[107],"proposed":[108,161],"mechanism,":[112],"can":[114],"leverage":[115],"association":[117],"between":[118],"relations":[119],"their":[121],"corresponding":[122],"attributes.":[124],"addition,":[126],"introduce":[128],"self-supervised":[131],"generate":[135],"unseen":[136],"positive":[137],"negative":[139],"examples,":[140],"thereby":[141],"making":[142],"our":[143,160],"approach":[144],"more":[145],"reliable":[146],"available.":[152],"evaluation":[155],"three":[157],"real-world":[158],"datasets,":[159],"model":[162],"outperformed":[163],"state-of-the-art":[164],"methods,":[165],"achieving":[166],"improvement":[168],"up":[170,176],"65.1%":[172],"Hits@1":[174],"52.6%":[178],"MRR":[180],"compared":[181],"best":[184],"competitor.":[185],"Our":[186],"implementation":[187],"code":[188],"available":[190],"at":[191],"https://github.com/learndatalab/RAKGE.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}