{"id":"https://openalex.org/W4401306695","doi":"https://doi.org/10.1145/3731120.3744594","title":"Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins","display_name":"Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4401306695","doi":"https://doi.org/10.1145/3731120.3744594"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744594","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744594?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744594?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008775203","display_name":"Lukas Gienapp","orcid":"https://orcid.org/0000-0001-5707-3751"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lukas Gienapp","raw_affiliation_strings":["University of Kassel, Kassel, Germany, ScaDS.AI, Leipzig, Germany, and hessian.AI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kassel, Kassel, Germany, ScaDS.AI, Leipzig, Germany, and hessian.AI, Darmstadt, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068128049","display_name":"Niklas Deckers","orcid":"https://orcid.org/0000-0001-6803-1223"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niklas Deckers","raw_affiliation_strings":["University of Kassel, Kassel, Germany and hessian.AI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kassel, Kassel, Germany and hessian.AI, Darmstadt, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["University of Kassel, Kassel, Germany, ScaDS.AI, Leipzig, Germany, and hessian.AI, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"University of Kassel, Kassel, Germany, ScaDS.AI, Leipzig, Germany, and hessian.AI, Darmstadt, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075371460","display_name":"Harrisen Scells","orcid":"https://orcid.org/0000-0001-9578-7157"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Harrisen Scells","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008775203"],"corresponding_institution_ids":["https://openalex.org/I106157433"],"apc_list":null,"apc_paid":null,"fwci":2.3431,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87415998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8579999804496765,"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/T10028","display_name":"Topic Modeling","score":0.8579999804496765,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7985000014305115,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.7929999828338623,"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/relevance","display_name":"Relevance (law)","score":0.784874439239502},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.683627188205719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5623274445533752},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4767533242702484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4445362687110901},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4216248393058777},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3395283818244934},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.13001087307929993},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12721100449562073},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06265619397163391}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.784874439239502},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.683627188205719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623274445533752},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4767533242702484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4445362687110901},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4216248393058777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3395283818244934},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.13001087307929993},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12721100449562073},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06265619397163391},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3731120.3744594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744594","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744594?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.21515","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21515","pdf_url":"https://arxiv.org/pdf/2407.21515","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2407.21515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.21515","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3731120.3744594","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744594","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744594?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3307378536","display_name":null,"funder_award_id":"Fellow","funder_id":"https://openalex.org/F4320308269","funder_display_name":"Alexander von Humboldt-Stiftung"},{"id":"https://openalex.org/G5082371171","display_name":null,"funder_award_id":"GA 101070014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7504899342","display_name":null,"funder_award_id":"101070014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G86606858","display_name":null,"funder_award_id":"GA 101070014","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401306695.pdf","grobid_xml":"https://content.openalex.org/works/W4401306695.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W4306316957","https://openalex.org/W3154280800","https://openalex.org/W4206121183","https://openalex.org/W3034368386","https://openalex.org/W2983128379","https://openalex.org/W3154670582","https://openalex.org/W2998702515","https://openalex.org/W4400530959","https://openalex.org/W3099700870","https://openalex.org/W3021397474","https://openalex.org/W6600424091","https://openalex.org/W3172762059","https://openalex.org/W2096733369","https://openalex.org/W4384639994","https://openalex.org/W2979826702"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W1967370444","https://openalex.org/W2157408137","https://openalex.org/W2150136235","https://openalex.org/W4312252109"],"abstract_inverted_index":{"Representation-based":[0],"retrieval":[1],"models,":[2],"so-called":[3],"bi-encoders,":[4],"estimate":[5],"the":[6,16,59,65,73,86,100,109],"relevance":[7],"of":[8,18,42,64,88,102,108],"a":[9,12,36,45,50,69,113],"document":[10],"to":[11,123],"query":[13],"by":[14,78],"calculating":[15],"similarity":[17],"their":[19],"respective":[20],"embeddings.":[21],"Current":[22],"state-of-the-art":[23],"bi-encoders":[24],"are":[25],"trained":[26],"using":[27,105],"an":[28],"expensive":[29],"training":[30,70,116],"regime":[31],"involving":[32],"knowledge":[33],"distillation":[34,104],"from":[35],"teacher":[37,46,103],"model":[38,67],"and":[39,120,128],"batch-sampling.":[40],"Instead":[41],"relying":[43],"on":[44],"model,":[47],"we":[48],"contribute":[49],"novel":[51],"parameter-free":[52],"loss":[53],"function":[54],"for":[55,75],"self-supervision":[56],"that":[57,96],"exploits":[58],"pre-trained":[60],"language":[61],"modeling":[62],"capabilities":[63,87],"encoder":[66],"as":[68],"signal,":[71],"eliminating":[72],"need":[74],"batch":[76],"sampling":[77],"performing":[79],"implicit":[80],"hard":[81],"negative":[82],"mining.":[83],"We":[84],"investigate":[85],"our":[89],"proposed":[90],"approach":[91],"through":[92],"extensive":[93],"experiments,":[94],"demonstrating":[95],"self-distillation":[97],"can":[98],"match":[99],"effectiveness":[101],"only":[106],"13.5%":[107],"data,":[110],"while":[111],"offering":[112],"speedup":[114],"in":[115],"time":[117],"between":[118],"3x":[119],"15x":[121],"compared":[122],"parametrized":[124],"losses.":[125],"All":[126],"code":[127],"data":[129],"is":[130],"made":[131],"openly":[132],"available.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2024-08-04T00:00:00"}