{"id":"https://openalex.org/W4293248928","doi":"https://doi.org/10.1145/3539813.3545127","title":"Filtering out Outliers in Learning to Rank","display_name":"Filtering out Outliers in Learning to Rank","publication_year":2022,"publication_date":"2022-08-23","ids":{"openalex":"https://openalex.org/W4293248928","doi":"https://doi.org/10.1145/3539813.3545127"},"language":"en","primary_location":{"id":"doi:10.1145/3539813.3545127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539813.3545127","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539813.3545127","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539813.3545127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009608294","display_name":"Federico Marcuzzi","orcid":"https://orcid.org/0000-0002-8141-8294"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Federico Marcuzzi","raw_affiliation_strings":["Universit\u00e0 Ca' Foscari Venezia, Venice, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Ca' Foscari Venezia, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030358452","display_name":"Claudio Lucchese","orcid":"https://orcid.org/0000-0002-2545-0425"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Lucchese","raw_affiliation_strings":["Universit\u00e0 Ca' Foscari Venezia, Venice, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Ca' Foscari Venezia, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066317336","display_name":"Salvatore Orlando","orcid":"https://orcid.org/0000-0002-4155-9797"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Salvatore Orlando","raw_affiliation_strings":["Universit\u00e0 Ca' Foscari Venezia, Venice, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Ca' Foscari Venezia, Venice, Italy","institution_ids":["https://openalex.org/I149461666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009608294"],"corresponding_institution_ids":["https://openalex.org/I149461666"],"apc_list":null,"apc_paid":null,"fwci":0.9283,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78740788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"214","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9986000061035156,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9980999827384949,"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/outlier","display_name":"Outlier","score":0.8648886680603027},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.6999472379684448},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6765190958976746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6601982712745667},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6502729654312134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373112201690674},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5539466738700867},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.5433623790740967},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5429392457008362},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.511475682258606},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.4978501796722412},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.47729384899139404},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42611193656921387},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41215208172798157},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21332260966300964},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.16461047530174255}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8648886680603027},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.6999472379684448},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6765190958976746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601982712745667},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6502729654312134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373112201690674},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5539466738700867},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.5433623790740967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5429392457008362},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.511475682258606},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.4978501796722412},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.47729384899139404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42611193656921387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41215208172798157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21332260966300964},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.16461047530174255},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539813.3545127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539813.3545127","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539813.3545127","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5004960","is_oa":true,"landing_page_url":"http://hdl.handle.net/10278/5004960","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3539813.3545127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539813.3545127","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539813.3545127","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293248928.pdf","grobid_xml":"https://content.openalex.org/works/W4293248928.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1967533108","https://openalex.org/W1982530130","https://openalex.org/W2113640060","https://openalex.org/W2162059449","https://openalex.org/W2296073425","https://openalex.org/W2296719434","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2798663050","https://openalex.org/W3035546924","https://openalex.org/W3156332500","https://openalex.org/W4205282737","https://openalex.org/W4251560691"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3137904399","https://openalex.org/W4310224730","https://openalex.org/W4310492845","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W3094138326","https://openalex.org/W4296079469"],"abstract_inverted_index":{"Outlier":[0],"data":[1,86],"points":[2],"are":[3,66],"known":[4],"to":[5,54],"affect":[6],"negatively":[7],"the":[8,20,73],"learning":[9,74],"process":[10],"of":[11,72,84],"regression":[12],"or":[13],"classification":[14],"models,":[15],"yet":[16],"their":[17],"impact":[18],"in":[19,69],"learning-to-rank":[21,37],"scenario":[22],"has":[23],"not":[24],"been":[25],"thoroughly":[26],"investigated":[27],"so":[28],"far.":[29],"In":[30],"this":[31],"work":[32],"we":[33],"propose":[34],"SOUR,":[35],"a":[36,81,90],"method":[38],"that":[39,65,79,98],"detects":[40],"and":[41,97,103],"removes":[42],"outliers":[43],"before":[44,88],"building":[45],"an":[46],"effective":[47],"ranking":[48],"model.":[49],"We":[50],"limit":[51],"our":[52],"analysis":[53],"gradient":[55],"boosting":[56],"decision":[57],"trees,":[58],"where":[59],"SOUR":[60,99],"searches":[61],"for":[62],"outlier":[63,85,104],"instances":[64,87],"incorrectly":[67],"ranked":[68],"several":[70],"iterations":[71],"process.":[75],"Extensive":[76],"experiments":[77],"show":[78],"removing":[80],"limited":[82],"number":[83],"re-training":[89],"new":[91],"model":[92],"provides":[93],"statistically":[94],"significant":[95],"improvements,":[96],"outperforms":[100],"state-of-the-art":[101],"de-noising":[102],"detection":[105],"methods.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-08-27T00:00:00"}