{"id":"https://openalex.org/W4414487480","doi":"https://doi.org/10.1145/3746252.3761651","title":"A Large-Scale Web Search Dataset for Federated Online Learning to Rank","display_name":"A Large-Scale Web Search Dataset for Federated Online Learning to Rank","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4414487480","doi":"https://doi.org/10.1145/3746252.3761651"},"language":"en","primary_location":{"id":"doi:10.1145/3746252.3761651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761651","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039793436","display_name":"Marcel Gregoriadis","orcid":"https://orcid.org/0000-0001-5094-0111"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcel Gregoriadis","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5094-0111","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003483119","display_name":"Jingwei Kang","orcid":"https://orcid.org/0009-0003-9283-4060"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jingwei Kang","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"raw_orcid":"https://orcid.org/0009-0003-9283-4060","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042627015","display_name":"Johan Pouwelse","orcid":"https://orcid.org/0000-0002-9882-1506"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Johan Pouwelse","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-9882-1506","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1081,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83079913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6387","last_page":"6391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.957099974155426,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9426000118255615,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6748999953269958},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6646000146865845},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6082000136375427},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5950000286102295},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5863000154495239},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.5169000029563904},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.4291999936103821},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.42260000109672546},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248999714851379},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6748999953269958},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6646000146865845},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5478000044822693},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.5169000029563904},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.42260000109672546},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C171089853","wikidata":"https://www.wikidata.org/wiki/Q7094123","display_name":"Online search","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2777622855","wikidata":"https://www.wikidata.org/wiki/Q7901844","display_name":"User information","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761651","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.12353","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.12353","pdf_url":"https://arxiv.org/pdf/2508.12353","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:10.1145/3746252.3761651","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761651","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 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4653258674","display_name":null,"funder_award_id":"BLOCK.2019.004","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"centralized":[1],"collection":[2],"of":[3,45,55,67,90],"search":[4,76],"interaction":[5],"logs":[6],"for":[7],"training":[8,29],"ranking":[9],"models":[10],"raises":[11],"significant":[12],"privacy":[13],"concerns.":[14],"Federated":[15],"Online":[16],"Learning":[17],"to":[18],"Rank":[19],"(FOLTR)":[20],"offers":[21],"a":[22,73],"privacy-preserving":[23],"alternative":[24],"by":[25,93],"enabling":[26,103],"collaborative":[27],"model":[28],"without":[30],"sharing":[31],"raw":[32],"user":[33,50,95,105],"data.":[34],"However,":[35],"benchmarks":[36,92],"in":[37],"FOLTR":[38],"are":[39],"largely":[40],"based":[41],"on":[42],"random":[43],"partitioning":[44],"classical":[46],"learning-to-rank":[47],"datasets,":[48],"simulated":[49],"clicks,":[51],"and":[52,63,100,109],"the":[53,65],"assumption":[54],"synchronous":[56],"client":[57],"participation.":[58],"This":[59],"oversimplifies":[60],"real-world":[61],"dynamics":[62],"undermines":[64],"realism":[66],"experimental":[68],"results.":[69],"We":[70],"present":[71],"AOL4FOLTR,":[72],"large-scale":[74],"web":[75],"dataset":[77,86],"with":[78],"2.6":[79],"million":[80],"queries":[81],"from":[82],"10,000":[83],"users.":[84],"Our":[85],"addresses":[87],"key":[88],"limitations":[89],"existing":[91],"including":[94],"identifiers,":[96],"real":[97],"click":[98],"data,":[99],"query":[101],"timestamps,":[102],"realistic":[104],"partitioning,":[106],"behavior":[107],"modeling,":[108],"asynchronous":[110],"federated":[111],"learning":[112],"scenarios.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
