{"id":"https://openalex.org/W7167927453","doi":"https://doi.org/10.1145/3805712.3809731","title":"Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors","display_name":"Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167927453","doi":"https://doi.org/10.1145/3805712.3809731"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809731","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809731","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809731","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060901174","display_name":"Patrick Iff","orcid":"https://orcid.org/0000-0001-5979-4915"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Patrick Iff","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-5979-4915","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140419494","display_name":"Paul Br\u00fcgger","orcid":"https://orcid.org/0009-0005-1208-7320"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Br\u00fcgger","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0005-1208-7320","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001468122","display_name":"Marcin Chrapek","orcid":"https://orcid.org/0009-0009-7654-6038"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marcin Chrapek","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0009-7654-6038","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140404565","display_name":"David Kochergin","orcid":"https://orcid.org/0009-0000-9420-6760"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Kochergin","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-9420-6760","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056549312","display_name":"Maciej Besta","orcid":"https://orcid.org/0000-0002-6550-7916"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maciej Besta","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6550-7916","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1333-9797","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.22990000247955322,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.22990000247955322,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13860000669956207,"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":0.13689999282360077,"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/embedding","display_name":"Embedding","score":0.8048999905586243},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7312999963760376},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.657800018787384},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6435999870300293},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6306999921798706},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.620199978351593},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5098999738693237}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8048999905586243},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7312999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6611999869346619},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.657800018787384},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6435999870300293},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C161986146","wikidata":"https://www.wikidata.org/wiki/Q4896845","display_name":"Best bin first","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C136736807","wikidata":"https://www.wikidata.org/wiki/Q818943","display_name":"Range query (database)","level":5,"score":0.27950000762939453},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809731","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809731","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809731","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809731","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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1172902973","https://openalex.org/W1977182282","https://openalex.org/W1978475816","https://openalex.org/W1986693891","https://openalex.org/W2000882268","https://openalex.org/W2015574730","https://openalex.org/W2017851434","https://openalex.org/W2063319420","https://openalex.org/W2086179657","https://openalex.org/W2086504823","https://openalex.org/W2096077837","https://openalex.org/W2097117768","https://openalex.org/W2099253838","https://openalex.org/W2110026675","https://openalex.org/W2111006384","https://openalex.org/W2118123209","https://openalex.org/W2118269922","https://openalex.org/W2125671345","https://openalex.org/W2133296809","https://openalex.org/W2133995768","https://openalex.org/W2144265691","https://openalex.org/W2147717514","https://openalex.org/W2162006472","https://openalex.org/W2165558283","https://openalex.org/W2202454807","https://openalex.org/W2294518132","https://openalex.org/W2397173492","https://openalex.org/W2427312773","https://openalex.org/W2464915613","https://openalex.org/W2523268797","https://openalex.org/W2887218294","https://openalex.org/W2901613577","https://openalex.org/W2939574508","https://openalex.org/W2949985202","https://openalex.org/W3007299504","https://openalex.org/W3020084632","https://openalex.org/W3028864969","https://openalex.org/W3029079605","https://openalex.org/W3037277842","https://openalex.org/W3037818944","https://openalex.org/W3084228038","https://openalex.org/W3085011441","https://openalex.org/W3089996945","https://openalex.org/W3094858795","https://openalex.org/W3174809957","https://openalex.org/W3196447082","https://openalex.org/W4242246215","https://openalex.org/W4246904949","https://openalex.org/W4306317701","https://openalex.org/W4367046898","https://openalex.org/W4381329135","https://openalex.org/W4385653226","https://openalex.org/W4393183654","https://openalex.org/W4399174383","https://openalex.org/W4399175194","https://openalex.org/W4403319937","https://openalex.org/W4405133457","https://openalex.org/W4405623265","https://openalex.org/W4405623356","https://openalex.org/W4411403204","https://openalex.org/W4411403463","https://openalex.org/W4413986310","https://openalex.org/W4417049589"],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1,40,77,178],"embedding":[2,42,85,91,119],"models":[3,92],"for":[4,121,185],"text,":[5],"image,":[6],"audio,":[7],"and":[8,20,105,138,164],"video":[9],"drive":[10],"progress":[11],"across":[12,154],"multiple":[13],"domains,":[14],"including":[15],"retrieval-augmented":[16],"generation,":[17],"recommendation":[18],"systems,":[19],"others.":[21],"Many":[22],"of":[23,102,117,124,159],"these":[24],"applications":[25],"require":[26],"an":[27,66],"efficient":[28],"method":[29,184],"to":[30,36,150],"retrieve":[31],"items":[32],"that":[33,93,175],"are":[34],"close":[35],"a":[37,46,54,74,99],"given":[38],"query":[39,165],"the":[41,51,78,114,122,180],"space":[43],"while":[44],"satisfying":[45],"filter":[47,156],"condition":[48],"based":[49],"on":[50,70,146],"item's":[52],"attributes,":[53],"problem":[55],"known":[56],"as":[57,136],"filtered":[58],"approximate":[59],"nearest":[60],"neighbor":[61],"search":[62],"(FANNS).":[63],"By":[64],"performing":[65],"in-depth":[67],"literature":[68],"analysis":[69],"FANNS,":[71],"we":[72,112],"identify":[73],"key":[75,173],"gap":[76],"research":[79],"landscape:":[80],"publicly":[81],"available":[82],"datasets":[83],"with":[84,131],"vectors":[86,120],"from":[87],"state-of-the-art":[88],"transformer-based":[89,118],"text":[90],"contain":[94],"abundant":[95],"real-world":[96,133],"attributes":[97,134],"covering":[98],"broad":[100],"spectrum":[101],"attribute":[103],"types":[104],"value":[106],"distributions.":[107],"To":[108],"fill":[109],"this":[110],"gap,":[111],"introduce":[113],"arxiv-for-fanns":[115],"dataset":[116,149,162],"abstracts":[123],"over":[125],"2.7":[126],"million":[127],"arXiv":[128],"papers,":[129],"enriched":[130],"11":[132],"such":[135],"authors":[137],"categories.":[139],"We":[140,167],"benchmark":[141],"eleven":[142],"different":[143,155],"FANNS":[144,183],"methods":[145],"our":[147,169],"new":[148],"evaluate":[151],"their":[152,186],"performance":[153],"types,":[157],"numbers":[158],"retrieved":[160],"neighbors,":[161],"scales,":[163],"selectivities.":[166],"distill":[168],"findings":[170],"into":[171],"eight":[172],"observations":[174],"guide":[176],"users":[177],"selecting":[179],"most":[181],"suitable":[182],"specific":[187],"use":[188],"cases.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}