{"id":"https://openalex.org/W7102771652","doi":"https://doi.org/10.1145/3731443.3771365","title":"Parameter Averaging in Link Prediction","display_name":"Parameter Averaging in Link Prediction","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7102771652","doi":"https://doi.org/10.1145/3731443.3771365"},"language":null,"primary_location":{"id":"doi:10.1145/3731443.3771365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771365","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731443.3771365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rupesh Sapkota","orcid":"https://orcid.org/0009-0009-3928-1130"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Rupesh Sapkota","raw_affiliation_strings":["Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0009-0009-3928-1130","affiliations":[{"raw_affiliation_string":"Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Caglar Demir","orcid":"https://orcid.org/0000-0001-8970-3850"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Caglar Demir","raw_affiliation_strings":["Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8970-3850","affiliations":[{"raw_affiliation_string":"Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arnab Sharma","orcid":"https://orcid.org/0009-0007-8515-5253"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arnab Sharma","raw_affiliation_strings":["Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0009-0007-8515-5253","affiliations":[{"raw_affiliation_string":"Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":null,"display_name":"Axel-Cyrille Ngonga Ngomo","orcid":"https://orcid.org/0000-0001-7112-3516"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Axel-Cyrille Ngonga Ngomo","raw_affiliation_strings":["Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7112-3516","affiliations":[{"raw_affiliation_string":"Heinz Nixdorf Institute, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75449193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9754999876022339,"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":0.9754999876022339,"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":0.0071000000461936,"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"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.004900000058114529,"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/generalization","display_name":"Generalization","score":0.6283000111579895},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.604200005531311},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.5698000192642212},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5307999849319458},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4494999945163727},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42289999127388},{"id":"https://openalex.org/keywords/multiple-models","display_name":"Multiple Models","score":0.36959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747999787330627},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43959999084472656},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731443.3771365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771365","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.25361","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.25361","pdf_url":"https://arxiv.org/pdf/2510.25361","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731443.3771365","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771365","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-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":{"Ensemble":[0],"methods":[1],"are":[2,48],"widely":[3],"employed":[4],"to":[5,33],"improve":[6],"generalization":[7,141],"in":[8,27,98],"machine":[9],"learning.":[10],"This":[11],"has":[12,54],"also":[13],"prompted":[14],"the":[15,21,42,45,60,130,134,140,161,169,188],"adoption":[16],"of":[17,41,63,105,133],"ensemble":[18,135,164],"learning":[19],"for":[20,117],"knowledge":[22],"graph":[23],"embedding":[24],"(KGE)":[25],"models":[26,38,66,176],"performing":[28],"link":[29,157],"prediction.":[30],"Typical":[31],"approaches":[32,76,155],"this":[34,52,89],"end":[35],"train":[36],"multiple":[37,65,86],"as":[39,182],"part":[40],"ensemble,":[43],"and":[44,69,115,177],"diverse":[46,197],"predictions":[47],"then":[49],"averaged.":[50],"However,":[51],"approach":[53,126,172,192],"some":[55],"significant":[56],"drawbacks.":[57],"For":[58],"instance,":[59],"computational":[61],"overhead":[62],"training":[64,85,110],"increases":[67],"latency":[68],"memory":[70],"overhead.":[71],"In":[72,88],"contrast,":[73],"model":[74,93,106,136],"merging":[75],"offer":[77],"a":[78,102,109,145],"promising":[79],"alternative":[80],"that":[81,127,187],"does":[82],"not":[83],"require":[84],"models.":[87,100],"work,":[90],"we":[91,122,167],"introduce":[92],"merging,":[94],"specifically":[95],"weighted":[96,153,170,190],"averaging,":[97],"KGE":[99,175],"Herein,":[101],"running":[103,131],"average":[104,132],"parameters":[107,137],"from":[108],"epoch":[111],"onward":[112],"is":[113],"maintained":[114],"used":[116],"predictions.":[118],"To":[119],"address":[120],"this,":[121],"additionally":[123],"propose":[124],"an":[125],"selectively":[128],"updates":[129],"only":[138],"when":[139],"performance":[142,195],"improves":[143,194],"on":[144,156],"validation":[146],"dataset.":[147],"We":[148],"evaluate":[149,168],"these":[150],"two":[151],"different":[152],"averaging":[154,171,191],"prediction":[158],"tasks,":[159],"comparing":[160],"state-of-the-art":[162],"benchmark":[163],"approach.":[165],"Additionally,":[166],"considering":[173],"literal-augmented":[174],"multi-hop":[178],"query":[179],"answering":[180],"tasks":[181],"well.":[183],"The":[184],"results":[185],"demonstrate":[186],"proposed":[189],"consistently":[193],"across":[196],"evaluation":[198],"settings.":[199]},"counts_by_year":[],"updated_date":"2025-12-10T02:49:46.989445","created_date":"2025-10-31T00:00:00"}