{"id":"https://openalex.org/W7166139595","doi":"https://doi.org/10.48550/arxiv.2606.26973","title":"Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning","display_name":"Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166139595","doi":"https://doi.org/10.48550/arxiv.2606.26973"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26973","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":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.2606.26973","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053595913","display_name":"Jiahe Chen","orcid":"https://orcid.org/0009-0009-0424-6941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiahe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139433774","display_name":"Qian Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139450217","display_name":"Qiyuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012171008","display_name":"Jiaying He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jiaying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139421463","display_name":"Jintai Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jintai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139456143","display_name":"Jian Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139406249","display_name":"Hongxia Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hongxia","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.38600000739097595,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.38600000739097595,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.362199991941452,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09839999675750732,"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/leverage","display_name":"Leverage (statistics)","score":0.649399995803833},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5449000000953674},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.5367000102996826},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5009999871253967},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43299999833106995},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3571999967098236},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.3434999883174896}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.5367000102996826},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4722000062465668},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45739999413490295},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C122748992","wikidata":"https://www.wikidata.org/wiki/Q2029312","display_name":"Gradient analysis","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C160343418","wikidata":"https://www.wikidata.org/wiki/Q185256","display_name":"Rigidity (electromagnetism)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28529998660087585},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26973","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26973","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":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":{"Open-set":[0],"semi-supervised":[1],"learning":[2,62],"aims":[3],"to":[4,76,139],"leverage":[5],"unlabeled":[6,30],"data":[7],"that":[8,37,58,88,125,154],"may":[9,126],"contain":[10],"out-of-distribution":[11],"outliers":[12],"while":[13,121],"maintaining":[14],"performance":[15],"on":[16,148],"in-distribution":[17],"classes.":[18],"Existing":[19],"methods":[20],"mainly":[21],"follow":[22],"two":[23],"paradigms:":[24],"filtering":[25,44],"suspicious":[26],"samples":[27],"or":[28],"incorporating":[29],"objectives":[31],"with":[32,60,136],"soft":[33],"weighting.":[34],"We":[35,68,79,132],"argue":[36],"both":[38,167],"face":[39],"a":[40,85],"common":[41],"trade-off:":[42],"aggressive":[43],"can":[45,54],"discard":[46],"informative":[47],"but":[48],"hard":[49],"ID":[50],"samples,":[51],"whereas":[52],"utilization":[53],"introduce":[55],"auxiliary":[56,99,112],"gradients":[57,100],"conflict":[59],"supervised":[61,91],"when":[63],"pseudo":[64],"labels":[65],"are":[66],"wrong.":[67],"therefore":[69],"shift":[70],"the":[71,90,110,117,141],"focus":[72],"from":[73],"sample":[74],"selection":[75],"gradient-level":[77],"control.":[78],"propose":[80],"\\textit{Geometric":[81],"Gradient":[82],"Rectification}":[83],"(GGR),":[84],"plug-in":[86],"framework":[87],"uses":[89],"gradient":[92,106],"as":[93],"an":[94,102],"anchor":[95,142],"and":[96,150,163,170],"projects":[97],"conflicting":[98],"onto":[101],"admissible":[103],"region":[104],"in":[105,160,166],"space.":[107],"This":[108],"makes":[109],"applied":[111],"update":[113],"first-order":[114],"non-opposing":[115],"within":[116],"rectified":[118],"coordinate":[119],"block":[120],"preserving":[122],"orthogonal":[123],"components":[124],"still":[127],"carry":[128],"useful":[129],"representation":[130],"signals.":[131],"further":[133],"extend":[134],"GGR":[135,155],"subspace-aware":[137],"rectification":[138],"stabilize":[140],"under":[143],"noisy":[144],"mini-batch":[145],"gradients.":[146],"Experiments":[147],"CIFAR":[149],"ImageNet":[151],"benchmarks":[152],"show":[153],"improves":[156],"representative":[157],"OSSL":[158],"baselines":[159],"most":[161],"settings":[162],"yields":[164],"gains":[165],"closed-set":[168],"generalization":[169],"open-set":[171],"robustness.":[172],"Code":[173],"will":[174],"be":[175],"available":[176],"at":[177],"https://github.com/JiaheChen2002/GGR.":[178]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}