{"id":"https://openalex.org/W7155630244","doi":"https://doi.org/10.1145/3787279.3787295","title":"Patent Retrieval with Few-Shot Fine-Tuning and Quantized Embeddings","display_name":"Patent Retrieval with Few-Shot Fine-Tuning and Quantized Embeddings","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7155630244","doi":"https://doi.org/10.1145/3787279.3787295"},"language":null,"primary_location":{"id":"doi:10.1145/3787279.3787295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3787295","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 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787279.3787295","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042290609","display_name":"Renukswamy Chikkamath","orcid":"https://orcid.org/0000-0002-6010-670X"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Renukswamy Chikkamath","raw_affiliation_strings":["Informatics and Mathematics, Hochschule Munchen, Munich, Bavaria, Germany,"],"raw_orcid":"https://orcid.org/0000-0002-6010-670X","affiliations":[{"raw_affiliation_string":"Informatics and Mathematics, Hochschule Munchen, Munich, Bavaria, Germany,","institution_ids":["https://openalex.org/I174004417"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012142","display_name":"Linda Andersson","orcid":"https://orcid.org/0000-0002-5743-7778"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Linda Andersson","raw_affiliation_strings":["Computer science, University of Vienna, Vienna, Austria,"],"raw_orcid":"https://orcid.org/0000-0001-9288-0954","affiliations":[{"raw_affiliation_string":"Computer science, University of Vienna, Vienna, Austria,","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046756404","display_name":"Markus Endres","orcid":"https://orcid.org/0000-0002-6436-559X"},"institutions":[{"id":"https://openalex.org/I174004417","display_name":"Munich University of Applied Sciences","ror":"https://ror.org/012k1v959","country_code":"DE","type":"education","lineage":["https://openalex.org/I174004417"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Endres","raw_affiliation_strings":["Informatics and Mathematics, Hochschule Munchen, Munich, Bavaria, Germany,"],"raw_orcid":"https://orcid.org/0000-0002-6436-559X","affiliations":[{"raw_affiliation_string":"Informatics and Mathematics, Hochschule Munchen, Munich, Bavaria, Germany,","institution_ids":["https://openalex.org/I174004417"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042290609"],"corresponding_institution_ids":["https://openalex.org/I174004417"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84212173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.9440000057220459,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.9440000057220459,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.0066999997943639755,"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":0.0027000000700354576,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7473999857902527},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4408000111579895},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3564999997615814},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.326200008392334}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7473999857902527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6636999845504761},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41499999165534973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41200000047683716},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26829999685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787279.3787295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3787295","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 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787279.3787295","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787279.3787295","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 2025 9th International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.45998793840408325,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1967684050","https://openalex.org/W2090719489","https://openalex.org/W2599678337","https://openalex.org/W2889961245","https://openalex.org/W2908935617","https://openalex.org/W2925605018","https://openalex.org/W2975532892","https://openalex.org/W3058517477","https://openalex.org/W3080998698","https://openalex.org/W3094204664","https://openalex.org/W3100806282","https://openalex.org/W3145477840","https://openalex.org/W3147292006","https://openalex.org/W3177415603","https://openalex.org/W3183039454","https://openalex.org/W4226146586","https://openalex.org/W4252076394","https://openalex.org/W4323520175","https://openalex.org/W4362640873","https://openalex.org/W4389038701","https://openalex.org/W4399114216","https://openalex.org/W4402858670","https://openalex.org/W4404281104"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"search":[1,55,102],"using":[2],"embedding":[3,92],"models":[4,62],"has":[5],"emerged":[6],"as":[7],"a":[8,31,98,105,121],"powerful":[9],"alternative":[10],"to":[11,112,140],"traditional":[12],"keyword-based":[13],"patent":[14,32,38],"retrieval,":[15],"yet":[16],"real-world":[17],"deployment":[18],"faces":[19],"challenges":[20],"in":[21,101,108],"computational":[22],"efficiency":[23],"and":[24,41,59,104],"cost.":[25],"We":[26,69],"address":[27],"this":[28],"by":[29],"introducing":[30],"pair":[33],"dataset":[34],"constructed":[35],"from":[36],"US":[37],"first":[39],"claims":[40],"abstracts":[42],"that":[43,71],"enables":[44],"efficient":[45],"fine-tuning":[46,79,129],"of":[47,146],"general-purpose":[48],"embeddings.":[49],"Our":[50,116],"approach":[51],"outperforms":[52],"both":[53],"European":[54],"report-based":[56],"citation":[57],"pairs":[58,75],"existing":[60],"retrieval":[61],"on":[63,142],"the":[64,84,147,150],"CLEF-IP":[65],"2011":[66],"English":[67],"benchmark.":[68],"show":[70],"even":[72],"5":[73],"training":[74],"suffice":[76],"for":[77,86,152],"domain-specific":[78],"(6-14%":[80],"MAP@100":[81,123],"gain),":[82],"eliminating":[83],"need":[85,151],"costly":[87],"large-scale":[88],"training.":[89],"By":[90],"incorporating":[91],"quantization,":[93],"we":[94],"achieve":[95],"at":[96],"least":[97],"30\u00d7":[99],"reduction":[100],"time":[103],"32\u00d7":[106],"decrease":[107],"memory":[109],"usage":[110],"compared":[111,139],"full-sized":[113],"embeddings":[114],"search.":[115],"results":[117],"demonstrate":[118],"configurations":[119],"achieving":[120],"22.5%":[122],"improvement":[124],"over":[125],"state-of-the-art.":[126],"However,":[127],"excessive":[128],"can":[130],"degrade":[131],"performance,":[132],"BGE-base":[133],"drops":[134],"5\u20136%":[135],"with":[136],"10,000":[137],"samples":[138],"tuning":[141],"just":[143],"5\u2013250,":[144],"regardless":[145],"dataset,":[148],"highlighting":[149],"strategic":[153],"sample":[154],"selection.":[155]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-26T00:00:00"}