{"id":"https://openalex.org/W3136623851","doi":null,"title":"Minimal conditions analysis of gradient-based reconstruction in Federated Learning","display_name":"Minimal conditions analysis of gradient-based reconstruction in Federated Learning","publication_year":2020,"publication_date":"2020-10-29","ids":{"openalex":"https://openalex.org/W3136623851","mag":"3136623851"},"language":"en","primary_location":{"id":"mag:3136623851","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.15718","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://export.arxiv.org/pdf/2010.15718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026065808","display_name":"Jia Qian","orcid":"https://orcid.org/0000-0002-6827-3983","observed_orcids":["https://orcid.org/0000-0002-6827-3983"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Qian","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6827-3983","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030105825","display_name":"Hiba Nassar","orcid":"https://orcid.org/0000-0003-0250-626X","observed_orcids":["https://orcid.org/0000-0003-0250-626X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiba Nassar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018292103","display_name":"Lars Kai Hansen","orcid":"https://orcid.org/0000-0003-0442-5877","observed_orcids":["https://orcid.org/0000-0003-0442-5877"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lars Kai Hansen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0442-5877","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":2,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9940999746322632,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9940999746322632,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0008999999845400453,"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":0.0007999999797903001,"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/gradient-based-reconstruction","display_name":"gradient-based reconstruction","score":0.7459999918937683},{"id":"https://openalex.org/keywords/federated-learning","display_name":"federated learning","score":0.8840000033378601},{"id":"https://openalex.org/keywords/orthogonality-regularization","display_name":"orthogonality regularization","score":0.8420000076293945},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7319999933242798},{"id":"https://openalex.org/keywords/fully-connected-neural-network","display_name":"fully connected neural network","score":0.6480000019073486},{"id":"https://openalex.org/keywords/image-reconstruction","display_name":"image reconstruction","score":0.546999990940094},{"id":"https://openalex.org/keywords/fmri","display_name":"functional MRI","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.890518307685852},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.656018078327179},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.6267033219337463},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6215760707855225},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5989421010017395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5984169244766235},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5849363207817078},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5311647057533264},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5181375741958618},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49840521812438965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4069388508796692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3944733738899231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34742945432662964},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12128067016601562},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.11925366520881653},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3136623851","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.15718","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3136623851","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.15718","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1473189865","https://openalex.org/W2051434435","https://openalex.org/W2109426455","https://openalex.org/W2535838896","https://openalex.org/W2803968356","https://openalex.org/W2951368041","https://openalex.org/W2964162474","https://openalex.org/W2970408908","https://openalex.org/W2990595670","https://openalex.org/W2995022099","https://openalex.org/W3000479830","https://openalex.org/W3014541599","https://openalex.org/W3085804918","https://openalex.org/W3094356870"],"related_works":["https://openalex.org/W3096355197","https://openalex.org/W3175192640","https://openalex.org/W3094356870","https://openalex.org/W3035515196","https://openalex.org/W3022022653","https://openalex.org/W7221811801","https://openalex.org/W6912791978","https://openalex.org/W7160657345","https://openalex.org/W7140227874","https://openalex.org/W6922836572"],"abstract_inverted_index":{"The":[0],"input":[1,50,144],"data":[2,173],"from":[3],"a":[4,28,48,59,73,107],"neural":[5,61],"network":[6,56,62],"may":[7,51],"be":[8,52,88],"reconstructed":[9,89],"using":[10,58,168],"knowledge":[11],"of":[12,15,43,55,78,93,114,137,158],"the":[13,40,84,91,104,111,117,135],"gradients":[14],"that":[16,47],"network,":[17],"as":[18],"demonstrated":[19],"by":[20,123],"\\cite{zhu2019deep}.":[21],"By":[22],"imposing":[23],"prior":[24],"information":[25],"and":[26,34,129,153,166,171,178],"utilising":[27],"uniform":[29],"initialization":[30],"we":[31,45,68,133,161],"demonstrate":[32],"faster":[33],"more":[35],"accurate":[36],"image":[37],"reconstruction.":[38],"Exploring":[39],"theoretical":[41,164],"limits":[42],"reconstruction,":[44],"show":[46],"single":[49],"reconstructed,":[53],"regardless":[54],"depth":[57],"fully-connected":[60],"with":[63,98],"one":[64],"hidden":[65,94],"node.":[66],"Then":[67],"generalize":[69],"this":[70,82],"result":[71],"to":[72,102],"gradient":[74],"averaged":[75],"over":[76],"mini-batches":[77],"size":[79],"$B$.":[80],"In":[81],"case,":[83],"full":[85],"mini-batch":[86],"can":[87],"if":[90],"number":[92,113,136,157],"units":[95],"exceeds":[96],"$B$,":[97],"an":[99],"orthogonality":[100],"regularizer":[101],"improve":[103],"precision.":[105],"For":[106],"Convolutional":[108],"Neural":[109],"Network,":[110],"required":[112],"filters":[115],"in":[116],"first":[118],"convolutional":[119],"layer":[120],"is":[121,143,147,155],"decided":[122],"multiple":[124],"factors":[125],"(e.g.,":[126],"padding,":[127],"kernel":[128],"stride":[130],"size).":[131],"Therefore,":[132],"require":[134],"filters,":[138],"$h\\geq":[139],"(\\frac{d}{d^{'}})^2C$,":[140],"where":[141],"$d$":[142],"width,":[145],"$d^{'}$":[146],"output":[148],"width":[149],"after":[150],"convolution":[151],"kernel,":[152],"$C$":[154],"channel":[156],"input.":[159],"Finally,":[160],"validate":[162],"our":[163],"analysis":[165],"improvements":[167],"bio-medical":[169],"(fMRI)":[170],"benchmark":[172],"(MNIST,":[174],"Kuzushiji-MNIST,":[175],"CIFAR100,":[176],"ImageNet":[177],"face":[179],"images).":[180]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-29T00:00:00"}