{"id":"https://openalex.org/W7171564468","doi":"https://doi.org/10.48550/arxiv.2607.23388","title":"Directional Influence Function: Estimating Training Data Influence in Constrained Learning","display_name":"Directional Influence Function: Estimating Training Data Influence in Constrained Learning","publication_year":2026,"publication_date":"2026-07-25","ids":{"openalex":"https://openalex.org/W7171564468","doi":"https://doi.org/10.48550/arxiv.2607.23388"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.23388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.23388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.23388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143775230","display_name":"Xin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","raw_affiliation_strings":["Jeff"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jeff","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046903273","display_name":"R. T. Rockafellar","orcid":"https://orcid.org/0000-0003-1703-5069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rockafellar, R. Tyrrell","raw_affiliation_strings":["Jeff"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jeff","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143857831","display_name":"Xuegang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuegang","raw_affiliation_strings":["Jeff"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jeff","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5143799229","display_name":"Ban","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ban","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4138999879360199,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.4138999879360199,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11379999667406082,"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":0.1054999977350235,"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":0.8001999855041504},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5374000072479248},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35499998927116394},{"id":"https://openalex.org/keywords/constrained-optimization","display_name":"Constrained optimization","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8001999855041504},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5333999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5034000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3846000134944916},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2983643213","wikidata":"https://www.wikidata.org/wiki/Q6030225","display_name":"Influence function","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.23388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.23388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.23388","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.23388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"constrained":[1,76,122,143,199],"learning":[2,123],"becomes":[3,72],"increasingly":[4],"common,":[5],"models":[6],"are":[7],"trained":[8],"under":[9,176],"explicit":[10],"feasibility":[11],"requirements":[12],"to":[13,90,166],"enforce":[14],"fairness,":[15],"safety,":[16],"robustness,":[17],"regulariza-":[18],"tion,":[19],"and":[20,41,85,129,146,156,179,192],"physics":[21],"or":[22,68],"logic":[23],"constraints.":[24],"Understanding":[25],"how":[26,57,132],"training":[27,64,134],"samples":[28],"in-":[29],"fluence":[30],"the":[31,58,83,86,99,117],"model":[32],"solution":[33,59],"(e.g.,":[34],"learned":[35],"parameters)":[36],"is":[37,66],"crucial":[38],"for":[39,195],"interpretability":[40],"robustness.":[42],"The":[43],"classical":[44],"influence":[45,113],"function":[46],"(IF)":[47],"estimates":[48,91],"sample":[49,65],"contribu-":[50],"tions":[51],"via":[52],"local":[53],"sensitivity":[54],"analysis,":[55],"measuring":[56],"changes":[60,175],"when":[61],"a":[62,104,125],"specific":[63],"perturbed":[67],"removed.":[69],"However,":[70],"IF":[71,155,158],"unreli-":[73],"able":[74],"in":[75,198],"settings:":[77],"data":[78,135,177,196],"perturbations":[79],"can":[80],"reshape":[81],"both":[82],"objective":[84],"feasible":[87],"region,":[88],"leading":[89],"that":[92,107,148],"violate":[93],"feasibility.":[94],"In":[95],"response,":[96],"we":[97],"propose":[98],"Directional":[100],"Influence":[101],"Function":[102],"(DIF),":[103],"novel":[105],"estimator":[106],"explicitly":[108],"incorporates":[109],"these":[110],"constraints":[111],"into":[112],"estimation.":[114],"DIF":[115,141,165,170,188],"formulates":[116],"opti-":[118],"mality":[119],"conditions":[120],"of":[121],"as":[124,189],"variational":[126],"inequality":[127],"(VI)":[128],"ana-":[130],"lyzes":[131],"perturbing":[133],"affects":[136],"this":[137],"VI.":[138],"We":[139,162],"validate":[140],"on":[142],"linear":[144],"regression":[145],"demonstrate":[147],"it":[149],"recovers":[150],"leave-one-out":[151],"retraining":[152],"results,":[153],"whereas":[154],"penalty-based":[157],"exhibit":[159],"significant":[160],"bias.":[161],"further":[163],"apply":[164],"fairness-constrained":[167],"CNNs,":[168],"where":[169],"accurately":[171],"predicts":[172],"test":[173],"loss":[174],"removal":[178],"aligns":[180],"closely":[181],"with":[182],"actual":[183],"retraining.":[184],"Our":[185],"results":[186],"establish":[187],"an":[190],"efficient":[191],"reliable":[193],"tool":[194],"attribution":[197],"learning.":[200]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-07-29T00:00:00"}