{"id":"https://openalex.org/W4417090763","doi":"https://doi.org/10.1109/icmla66185.2025.00041","title":"Sliced-Wasserstein Distance-based Data Selection","display_name":"Sliced-Wasserstein Distance-based Data Selection","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4417090763","doi":"https://doi.org/10.1109/icmla66185.2025.00041"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.12918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092229478","display_name":"Julien Pallage","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA","FR"],"is_corresponding":true,"raw_author_name":"Julien Pallage","raw_affiliation_strings":["Polytechnique Montréal, Mila & GERAD,Department of Electrical Engineering,Montréal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montréal, Mila & GERAD,Department of Electrical Engineering,Montréal,Canada","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I45683168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032213221","display_name":"Antoine Lesage\u2010Landry","orcid":"https://orcid.org/0000-0001-9652-6557"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA","FR"],"is_corresponding":false,"raw_author_name":"Antoine Lesage-Landry","raw_affiliation_strings":["Polytechnique Montréal, Mila & GERAD,Department of Electrical Engineering,Montréal,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnique Montréal, Mila & GERAD,Department of Electrical Engineering,Montréal,Canada","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5092229478"],"corresponding_institution_ids":["https://openalex.org/I142476485","https://openalex.org/I45683168"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19395234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5655999779701233,"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":0.5655999779701233,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.07259999960660934,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.024800000712275505,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6987000107765198},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5508999824523926},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5461000204086304},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5260000228881836},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.43959999084472656},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.42910000681877136},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.388700008392334},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.3765000104904175},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3734000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305999994277954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6987000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5812000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580999851226807},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2639959","wikidata":"https://www.wikidata.org/wiki/Q1344778","display_name":"Distance measures","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icmla66185.2025.00041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00041","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:76388","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/76388/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2504.12918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12918","pdf_url":"https://arxiv.org/pdf/2504.12918","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":"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.2504.12918","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.12918","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":"pmh:oai:arXiv.org:2504.12918","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.12918","pdf_url":"https://arxiv.org/pdf/2504.12918","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417090763.pdf","grobid_xml":"https://content.openalex.org/works/W4417090763.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,113],"propose":[1],"a":[2,43,78,110,141],"new":[3],"unsupervised":[4],"anomaly":[5],"detection":[6],"method":[7,76,120,128,137],"based":[8],"on":[9,89,121],"the":[10,54,71,96,115],"sliced-Wasserstein":[11],"distance":[12,82],"for":[13,26,129,146],"training":[14,130],"data":[15,45,131],"selection":[16,46],"in":[17,33,109],"machine":[18,30],"learning":[19,31],"approaches.":[20],"Our":[21],"filtering":[22,116],"technique":[23],"is":[24],"interesting":[25],"decision-making":[27],"pipelines":[28],"deploying":[29],"models":[32],"critical":[34,101],"sectors,":[35],"e.g.,":[36],"electric":[37],"power":[38,91,107],"systems,":[39],"as":[40,93,138],"it":[41],"offers":[42],"conservative":[44],"and":[47,124],"an":[48],"optimal":[49],"transport":[50],"interpretation.":[51],"To":[52],"ensure":[53],"scalability":[55],"of":[56,70,106,118,140],"our":[57,87,119,127,136,147],"method,":[58],"we":[59,85,94,134],"provide":[60],"two":[61],"efficient":[62],"approximations.":[63],"The":[64,74],"first":[65,97,142],"approximation":[66],"processes":[67],"reduced-cardinality":[68],"representations":[69],"datasets":[72,123],"concurrently.":[73],"second":[75],"utilizes":[77],"computationally":[79],"lightweight":[80],"Euclidian":[81],"approximation.":[83],"Additionally,":[84],"focus":[86],"analysis":[88],"virtual":[90],"plants":[92],"open":[95],"dataset":[98],"showcasing":[99],"localized":[100],"peak":[102],"rebate":[103],"demand":[104],"response":[105],"systems":[108],"northern":[111],"climate.":[112],"present":[114],"patterns":[117],"synthetic":[122],"numerically":[125],"benchmark":[126,145],"selection.":[132],"Finally,":[133],"employ":[135],"part":[139],"load":[143],"forecasting":[144],"open-source":[148],"dataset.":[149]},"counts_by_year":[],"updated_date":"2026-05-11T08:15:01.531666","created_date":"2025-10-10T00:00:00"}