The LambdaGap Framework for Precision-Oriented Ranking

LambdaRank has proven effective for optimizing information retrieval metrics such as Normalized Discounted Cumulative Gain (NDCG). However, its application to Precision at document k (P@k) poses significant challenges because of the metric's unique definition, which heavily restricts the number...

Descripción completa

Detalles Bibliográficos
Autores: Adàlia, Ramon|||0009-0004-9458-1922, Sanjuan, Gemma|||0000-0002-1946-4345, Margalef, Tomàs|||0000-0001-6384-7389, Zamora, Ismael|||0000-0002-7700-0354
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:317648
Acceso en línea:https://ddd.uab.cat/record/317648
https://dx.doi.org/urn:doi:10.1145/3733235
Access Level:acceso abierto
Palabra clave:Learning to Rank
LambdaRank
Ranking Metric Optimization
id ES_3b37dae0f830be71d68c4bc5380fb0a7
oai_identifier_str oai:ddd.uab.cat:317648
network_acronym_str ES
network_name_str España
repository_id_str
spelling The LambdaGap Framework for Precision-Oriented RankingAdàlia, Ramon|||0009-0004-9458-1922Sanjuan, Gemma|||0000-0002-1946-4345Margalef, Tomàs|||0000-0001-6384-7389Zamora, Ismael|||0000-0002-7700-0354Learning to RankLambdaRankRanking Metric OptimizationLambdaRank has proven effective for optimizing information retrieval metrics such as Normalized Discounted Cumulative Gain (NDCG). However, its application to Precision at document k (P@k) poses significant challenges because of the metric's unique definition, which heavily restricts the number of effective training document pairs. This limitation diminishes the learning signal for relevant documents beyond the top k, potentially resulting in suboptimal performance. To overcome this, we propose LambdaGap, a ranking algorithm inspired by LambdaRank specifically tailored for optimizing P@k. LambdaGap replaces the pairwise weighting scheme in LambdaRank by one where pairs of documents within k positions in the ranking are masked out. We establish a theoretical link between LambdaGap and P@k by identifying the implicit metric optimized by the model. Furthermore, we introduce a new metric, Average Relevance Position beyond document k, which can be used in conjunction with LambdaRank to indirectly optimize for P@k. Our extensive experiments on publicly available datasets demonstrate the effectiveness of the proposed methods, yielding statistically significant improvements in P@k performance and highlighting their potential for more efficient training. 22025-01-0120252025-01-01Articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://ddd.uab.cat/record/317648https://dx.doi.org/urn:doi:10.1145/3733235reponame:Dipòsit Digital de Documents de la UABinstname:Universitat Autònoma de BarcelonaInglésengGeneralitat de Catalunya https://doi.org/10.13039/501100002809 2023-DI-00006open accesshttp://purl.org/coar/access_right/c_abf2Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:ddd.uab.cat:3176482026-06-06T12:50:31Z
dc.title.none.fl_str_mv The LambdaGap Framework for Precision-Oriented Ranking
title The LambdaGap Framework for Precision-Oriented Ranking
spellingShingle The LambdaGap Framework for Precision-Oriented Ranking
Adàlia, Ramon|||0009-0004-9458-1922
Learning to Rank
LambdaRank
Ranking Metric Optimization
title_short The LambdaGap Framework for Precision-Oriented Ranking
title_full The LambdaGap Framework for Precision-Oriented Ranking
title_fullStr The LambdaGap Framework for Precision-Oriented Ranking
title_full_unstemmed The LambdaGap Framework for Precision-Oriented Ranking
title_sort The LambdaGap Framework for Precision-Oriented Ranking
dc.creator.none.fl_str_mv Adàlia, Ramon|||0009-0004-9458-1922
Sanjuan, Gemma|||0000-0002-1946-4345
Margalef, Tomàs|||0000-0001-6384-7389
Zamora, Ismael|||0000-0002-7700-0354
author Adàlia, Ramon|||0009-0004-9458-1922
author_facet Adàlia, Ramon|||0009-0004-9458-1922
Sanjuan, Gemma|||0000-0002-1946-4345
Margalef, Tomàs|||0000-0001-6384-7389
Zamora, Ismael|||0000-0002-7700-0354
author_role author
author2 Sanjuan, Gemma|||0000-0002-1946-4345
Margalef, Tomàs|||0000-0001-6384-7389
Zamora, Ismael|||0000-0002-7700-0354
author2_role author
author
author
dc.subject.none.fl_str_mv Learning to Rank
LambdaRank
Ranking Metric Optimization
topic Learning to Rank
LambdaRank
Ranking Metric Optimization
description LambdaRank has proven effective for optimizing information retrieval metrics such as Normalized Discounted Cumulative Gain (NDCG). However, its application to Precision at document k (P@k) poses significant challenges because of the metric's unique definition, which heavily restricts the number of effective training document pairs. This limitation diminishes the learning signal for relevant documents beyond the top k, potentially resulting in suboptimal performance. To overcome this, we propose LambdaGap, a ranking algorithm inspired by LambdaRank specifically tailored for optimizing P@k. LambdaGap replaces the pairwise weighting scheme in LambdaRank by one where pairs of documents within k positions in the ranking are masked out. We establish a theoretical link between LambdaGap and P@k by identifying the implicit metric optimized by the model. Furthermore, we introduce a new metric, Average Relevance Position beyond document k, which can be used in conjunction with LambdaRank to indirectly optimize for P@k. Our extensive experiments on publicly available datasets demonstrate the effectiveness of the proposed methods, yielding statistically significant improvements in P@k performance and highlighting their potential for more efficient training.
publishDate 2025
dc.date.none.fl_str_mv 2
2025-01-01
2025
2025-01-01
dc.type.none.fl_str_mv Article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://ddd.uab.cat/record/317648
https://dx.doi.org/urn:doi:10.1145/3733235
url https://ddd.uab.cat/record/317648
https://dx.doi.org/urn:doi:10.1145/3733235
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Generalitat de Catalunya https://doi.org/10.13039/501100002809 2023-DI-00006
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Dipòsit Digital de Documents de la UAB
instname:Universitat Autònoma de Barcelona
instname_str Universitat Autònoma de Barcelona
reponame_str Dipòsit Digital de Documents de la UAB
collection Dipòsit Digital de Documents de la UAB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869406292335919104
score 15,812455

Similares en LA Referencia