{"id":"https://openalex.org/W4409455420","doi":"https://doi.org/10.14428/esann/2025.es2025-87","title":"Enhancing neural link predictors for temporal knowledge graphs with temporal regularisers","display_name":"Enhancing neural link predictors for temporal knowledge graphs with temporal regularisers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409455420","doi":"https://doi.org/10.14428/esann/2025.es2025-87"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2025.es2025-87","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-87","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-87","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2025.es2025-87","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018462865","display_name":"Manuel Dileo","orcid":"https://orcid.org/0000-0002-4861-455X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manuel Dileo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019106673","display_name":"Pasquale Minervini","orcid":"https://orcid.org/0000-0002-8442-602X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pasquale Minervini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035471624","display_name":"Matteo Zignani","orcid":"https://orcid.org/0000-0002-4808-4106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Zignani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002723662","display_name":"Sabrina Gaito","orcid":"https://orcid.org/0000-0003-3779-2809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabrina Gaito","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018462865"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0462,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93158827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9843999743461609,"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":0.9843999743461609,"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":0.9175999760627747,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6378129720687866},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.516588568687439},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.42140230536460876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3990866541862488},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10517522692680359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378129720687866},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.516588568687439},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.42140230536460876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3990866541862488},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10517522692680359}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2025.es2025-87","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-87","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-87","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2025.es2025-87","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-87","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-87","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1145458839","display_name":null,"funder_award_id":"PRIN 2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409455420.pdf","grobid_xml":"https://content.openalex.org/works/W4409455420.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1518185400","https://openalex.org/W3200586296","https://openalex.org/W2390279801","https://openalex.org/W4230332972","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W1998033311"],"abstract_inverted_index":{"The":[0],"problem":[1,30],"of":[2,11,36,44,56,59,74,134],"link":[3,138],"prediction":[4,139],"in":[5,15],"temporal":[6,20,60,75,92,121,137],"knowledge":[7,17],"graphs":[8],"(TKGs)":[9],"consists":[10],"finding":[12],"missing":[13],"links":[14],"the":[16,29,33,42,54,57,91,131,135],"base":[18,136],"under":[19],"constraints.Recently,":[21],"[4]":[22,102],"and":[23,80,94,110],"[8]":[24],"proposed":[25],"a":[26,97],"solution":[27],"to":[28],"inspired":[31],"by":[32,47,88],"canonical":[34],"decomposition":[35],"4-order":[37],"tensors,":[38],"where":[39],"they":[40],"regularise":[41],"representations":[43],"time":[45],"steps":[46],"learning":[48],"similar":[49],"transformation":[50],"for":[51,120],"adjacent":[52],"timestamps.However,":[53],"impact":[55],"choice":[58],"regularisation":[61,95],"terms":[62],"is":[63],"still":[64],"poorly":[65],"understood.In":[66],"this":[67],"work,":[68],"we":[69,85,115],"systematically":[70],"analyse":[71],"several":[72],"choices":[73],"regularisers":[76,119],"using":[77],"linear":[78,118],"functions":[79],"recurrent":[81],"architectures.In":[82],"our":[83],"experiments,":[84],"show":[86],"that":[87,117],"carefully":[89],"selecting":[90],"regulariser":[93],"weight,":[96],"simple":[98],"method":[99],"like":[100],"TNTComplEx":[101],"can":[103,128],"produce":[104],"comparable":[105],"results":[106],"with":[107],"state-of-the-art":[108],"methods":[109],"enhance":[111],"its":[112],"original":[113],"performance.Specifically,":[114],"observe":[116],"smoothing":[122],"based":[123],"on":[124],"specific":[125],"nuclear":[126],"norms":[127],"significantly":[129],"improve":[130],"predictive":[132],"accuracy":[133],"methods.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2025-10-10T00:00:00"}