{"id":"https://openalex.org/W4417029978","doi":"https://doi.org/10.48550/arxiv.2512.03578","title":"When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate","display_name":"When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4417029978","doi":"https://doi.org/10.48550/arxiv.2512.03578"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.03578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03578","pdf_url":"https://arxiv.org/pdf/2512.03578","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.03578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027132281","display_name":"Florent Forest","orcid":"https://orcid.org/0000-0001-6878-8752"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Forest, Florent","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005875291","display_name":"Anlei Wei","orcid":"https://orcid.org/0000-0003-1901-4237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Amaury","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079637160","display_name":"Olga Fink","orcid":"https://orcid.org/0000-0002-9546-1488"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fink, Olga","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027132281"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9376000165939331,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9376000165939331,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0348999984562397,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.003100000089034438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9289000034332275},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5536999702453613},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5126000046730042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.444599986076355},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.39879998564720154},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.38670000433921814},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.37229999899864197}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9289000034332275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6728000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6462000012397766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.03578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03578","pdf_url":"https://arxiv.org/pdf/2512.03578","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.03578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.03578","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.03578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03578","pdf_url":"https://arxiv.org/pdf/2512.03578","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4008620306","display_name":null,"funder_award_id":"200021_200461","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4785301346","display_name":"Genetik der elektrophysiologischen Antworten in den Antennen von Rhagoletis pomonella und R.mendax auf Reize durch chemische Wirtspflanzenduftstoffe.","funder_award_id":"20046","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G4836148144","display_name":null,"funder_award_id":"20002","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G7567274762","display_name":null,"funder_award_id":"200461","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8770402233","display_name":null,"funder_award_id":"200021 200461","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G993971353","display_name":null,"funder_award_id":"200021","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320320971","display_name":"Monash University","ror":"https://ror.org/02bfwt286"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4417029978.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time":[0,155],"series":[1],"extrinsic":[2],"regression":[3],"(TSER)":[4],"refers":[5],"to":[6,60,76,77,139,141,179],"the":[7,80,121,200,220],"task":[8],"of":[9,169,207],"predicting":[10],"a":[11,166,180,212],"continuous":[12],"target":[13],"variable":[14],"from":[15],"an":[16,157],"input":[17,186],"time":[18],"series.":[19],"It":[20],"appears":[21],"in":[22,199],"many":[23],"domains,":[24],"including":[25],"healthcare,":[26],"finance,":[27],"environmental":[28],"monitoring,":[29],"and":[30,37,137,195,227],"engineering.":[31],"In":[32],"these":[33,112,147,208],"settings,":[34],"accurate":[35],"predictions":[36,194],"trustworthy":[38],"reasoning":[39],"are":[40,203,229],"both":[41,190],"essential.":[42],"Although":[43],"state-of-the-art":[44],"TSER":[45],"models":[46],"achieve":[47],"strong":[48],"predictive":[49],"performance,":[50],"they":[51,116,197],"typically":[52],"operate":[53],"as":[54,72,108,205],"black":[55],"boxes,":[56],"making":[57],"it":[58],"difficult":[59],"understand":[61],"which":[62,191],"temporal":[63,135],"patterns":[64],"drive":[65,193],"their":[66],"decisions.":[67],"Post-hoc":[68],"interpretability":[69],"techniques,":[70],"such":[71],"feature":[73],"attribution,":[74],"aim":[75],"explain":[78],"how":[79],"model":[81],"arrives":[82],"at":[83,232],"its":[84],"predictions,":[85],"but":[86],"often":[87,124],"produce":[88],"coarse,":[89],"noisy,":[90],"or":[91,103],"unstable":[92],"explanations.":[93],"Recently,":[94],"inherently":[95,158],"interpretable":[96,159],"approaches":[97,113],"based":[98],"on":[99,120],"concepts,":[100],"additive":[101,214],"decompositions,":[102],"symbolic":[104],"regression,":[105],"have":[106],"emerged":[107],"promising":[109],"alternatives.":[110],"However,":[111],"remain":[114],"limited:":[115],"require":[117],"explicit":[118],"supervision":[119],"concepts":[122,171,210],"themselves,":[123],"cannot":[125],"capture":[126],"interactions":[127],"between":[128],"time-series":[129],"features,":[130,187],"lack":[131],"expressiveness":[132],"for":[133,154,162],"complex":[134],"patterns,":[136],"struggle":[138],"scale":[140],"high-dimensional":[142],"multivariate":[143],"data.":[144],"To":[145],"address":[146],"limitations,":[148],"we":[149],"propose":[150],"MAGNETS":[151,164],"(Mask-and-AGgregate":[152],"NEtwork":[153],"Series),":[156],"neural":[160],"architecture":[161],"TSER.":[163],"learns":[165],"compact":[167],"set":[168],"human-understandable":[170],"without":[172],"requiring":[173],"any":[174],"annotations.":[175],"Each":[176],"concept":[177],"corresponds":[178],"learned,":[181],"mask-based":[182],"aggregation":[183],"over":[184],"selected":[185],"explicitly":[188],"revealing":[189],"features":[192],"when":[196],"matter":[198],"sequence.":[201],"Predictions":[202],"formed":[204],"combinations":[206],"learned":[209],"through":[211],"transparent,":[213],"structure,":[215],"enabling":[216],"clear":[217],"insight":[218],"into":[219],"model's":[221],"decision":[222],"process.":[223],"The":[224],"code":[225],"implementation":[226],"datasets":[228],"publicly":[230],"available":[231],"https://github.com/FlorentF9/MAGNETS.":[233]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-12-05T00:00:00"}