Federated Learning With Privacy-Preserving Ensemble Attention Distillation

Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facil...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on medical imaging Ročník 42; číslo 7; s. 2057 - 2067
Hlavní autori: Gong, Xuan, Song, Liangchen, Vedula, Rishi, Sharma, Abhishek, Zheng, Meng, Planche, Benjamin, Innanje, Arun, Chen, Terrence, Yuan, Junsong, Doermann, David, Wu, Ziyan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.07.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:0278-0062, 1558-254X, 1558-254X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work. The central model is learned from local knowledge via ensemble attention distillation. Our technique uses decentralized and heterogeneous local data like existing FL approaches, but more importantly, it significantly reduces the risk of privacy leakage. We demonstrate that our method achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks.
AbstractList Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work. The central model is learned from local knowledge via ensemble attention distillation. Our technique uses decentralized and heterogeneous local data like existing FL approaches, but more importantly, it significantly reduces the risk of privacy leakage. We demonstrate that our method achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks.
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work. The central model is learned from local knowledge via ensemble attention distillation. Our technique uses decentralized and heterogeneous local data like existing FL approaches, but more importantly, it significantly reduces the risk of privacy leakage. We demonstrate that our method achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks.Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work. The central model is learned from local knowledge via ensemble attention distillation. Our technique uses decentralized and heterogeneous local data like existing FL approaches, but more importantly, it significantly reduces the risk of privacy leakage. We demonstrate that our method achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks.
Author Gong, Xuan
Vedula, Rishi
Doermann, David
Planche, Benjamin
Innanje, Arun
Sharma, Abhishek
Zheng, Meng
Song, Liangchen
Chen, Terrence
Wu, Ziyan
Yuan, Junsong
Author_xml – sequence: 1
  givenname: Xuan
  orcidid: 0000-0001-8303-633X
  surname: Gong
  fullname: Gong, Xuan
  email: xuangong@buffalo.edu
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 2
  givenname: Liangchen
  orcidid: 0000-0002-8366-5088
  surname: Song
  fullname: Song, Liangchen
  email: lsong8@buffalo.edu
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 3
  givenname: Rishi
  orcidid: 0000-0002-3205-3292
  surname: Vedula
  fullname: Vedula, Rishi
  email: rishisat@buffalo.edu
  organization: Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
– sequence: 4
  givenname: Abhishek
  surname: Sharma
  fullname: Sharma, Abhishek
  email: abhishek.sharma@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 5
  givenname: Meng
  surname: Zheng
  fullname: Zheng, Meng
  email: meng.zheng@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 6
  givenname: Benjamin
  orcidid: 0000-0002-6110-6437
  surname: Planche
  fullname: Planche, Benjamin
  email: benjamin.planche@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 7
  givenname: Arun
  surname: Innanje
  fullname: Innanje, Arun
  email: arun.innanje@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 8
  givenname: Terrence
  surname: Chen
  fullname: Chen, Terrence
  email: terrence.chen@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
– sequence: 9
  givenname: Junsong
  orcidid: 0000-0002-7324-7034
  surname: Yuan
  fullname: Yuan, Junsong
  email: jsyuan@buffalo.edu
  organization: Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
– sequence: 10
  givenname: David
  orcidid: 0000-0003-1639-4561
  surname: Doermann
  fullname: Doermann, David
  email: doermann@buffalo.edu
  organization: Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA
– sequence: 11
  givenname: Ziyan
  orcidid: 0000-0002-9774-7770
  surname: Wu
  fullname: Wu, Ziyan
  email: ziyan.wu@uii-ai.com
  organization: United Imaging Intelligence, Cambridge, MA, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36215346$$D View this record in MEDLINE/PubMed
BookMark eNp9kT1PHDEQhq2IKBwkfSQktFIamr3YY3vXWyICgehQKIiSzrK9s2C05wXbh8S_x5c7KCioRjN63vl698hOmAIS8pXROWO0-359eTEHCjDnwDgI8YHMmJSqBin-7ZAZhVbVlDawS_ZSuqOUCUm7T2SXN8AkF82M_DrDHqPJ2FcLNDH4cFP99fm2uor-0bin-ipiwvi4rp-GhEs7YnWcM4bsp1D98Cn7cTTr5DP5OJgx4Zdt3Cd_zk6vT87rxe-fFyfHi9px0ebaWjPQHlkPjR0kd7LDVnDRK1CopG0ds4pR16KynPU9t41rQYKRzgwFpHyfHG363sfpYYUp66VPDssWAadV0tACV-XSrinotzfo3bSKoWynQXEmqaIKCnW4pVZ2ib2-j35p4pN--VIB6AZwcUop4vCKMKrXRuhihF4bobdGFEnzRuJ8_v-mHI0f3xMebIQeEV_ndB2TolH8GXEak_k
CODEN ITMID4
CitedBy_id crossref_primary_10_1109_JIOT_2024_3416527
crossref_primary_10_1109_TMI_2025_3525581
crossref_primary_10_1007_s11227_024_06476_0
crossref_primary_10_2967_jnumed_124_268186
crossref_primary_10_1109_JBHI_2023_3319516
crossref_primary_10_1109_TMI_2024_3432388
crossref_primary_10_1109_TMC_2024_3517592
crossref_primary_10_1007_s11704_024_40065_x
crossref_primary_10_1109_MWC_016_2300523
crossref_primary_10_1016_j_imavis_2024_105246
crossref_primary_10_1109_TCE_2025_3541553
crossref_primary_10_1109_TR_2024_3474710
crossref_primary_10_3390_bdcc8090099
crossref_primary_10_1109_TMM_2023_3339588
crossref_primary_10_1109_JIOT_2023_3325822
crossref_primary_10_1007_s10462_024_10774_7
crossref_primary_10_1109_ACCESS_2024_3458911
Cites_doi 10.1109/CVPR.2018.00960
10.1007/978-3-030-58607-2_5
10.1007/978-3-030-58558-7_15
10.1016/j.media.2021.101992
10.1109/ICCV48922.2021.01480
10.1145/3097983.3098135
10.1007/s10994-009-5152-4
10.1109/CVPR46437.2021.00245
10.1162/neco.1991.3.1.79
10.1109/CVPR.2019.00528
10.1158/1078-0432.CCR-18-1233
10.1162/089976699300016737
10.1109/ICCV.2017.74
10.1145/1015330.1015432
10.1609/aaai.v33i01.3301590
10.1109/CVPR.2018.00813
10.1109/TMI.2014.2377694
10.1109/CVPR42600.2020.00241
10.1109/MNET.2018.1700202
10.1109/CVPR.2019.00128
10.1016/S0004-3702(02)00190-X
10.1109/CVPR.2017.369
10.1016/j.media.2020.101765
10.1109/CVPR42600.2020.01103
10.1109/CVPR.2017.754
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
DOI 10.1109/TMI.2022.3213244
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Materials Research Database
Civil Engineering Abstracts
Aluminium Industry Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Nursing & Allied Health Premium
Engineered Materials Abstracts
Biotechnology Research Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Corrosion Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList
MEDLINE
MEDLINE - Academic
Materials Research Database
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Engineering
EISSN 1558-254X
EndPage 2067
ExternalDocumentID 36215346
10_1109_TMI_2022_3213244
9915468
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Amazon Catalyst; Amazon
  funderid: 10.13039/100016443
GroupedDBID ---
-DZ
-~X
.GJ
0R~
29I
4.4
53G
5GY
5RE
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
ACPRK
AENEX
AETIX
AFRAH
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IBMZZ
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
VH1
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
RIG
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
ID FETCH-LOGICAL-c347t-bbaf0de1d26bf53c59e7434d828e85b7c1b810c7e8b31dd3b6c7252a5caf74303
IEDL.DBID RIE
ISICitedReferencesCount 24
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001022138900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0278-0062
1558-254X
IngestDate Sun Sep 28 02:49:21 EDT 2025
Sun Nov 09 08:42:47 EST 2025
Mon Jul 21 05:27:34 EDT 2025
Sat Nov 29 05:14:10 EST 2025
Tue Nov 18 22:28:57 EST 2025
Wed Aug 27 02:29:09 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 7
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c347t-bbaf0de1d26bf53c59e7434d828e85b7c1b810c7e8b31dd3b6c7252a5caf74303
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-8303-633X
0000-0002-8366-5088
0000-0003-1639-4561
0000-0002-3205-3292
0000-0002-6110-6437
0000-0002-7324-7034
0000-0002-9774-7770
PMID 36215346
PQID 2831508082
PQPubID 85460
PageCount 11
ParticipantIDs crossref_primary_10_1109_TMI_2022_3213244
crossref_citationtrail_10_1109_TMI_2022_3213244
pubmed_primary_36215346
ieee_primary_9915468
proquest_miscellaneous_2723814596
proquest_journals_2831508082
PublicationCentury 2000
PublicationDate 2023-07-01
PublicationDateYYYYMMDD 2023-07-01
PublicationDate_xml – month: 07
  year: 2023
  text: 2023-07-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on medical imaging
PublicationTitleAbbrev TMI
PublicationTitleAlternate IEEE Trans Med Imaging
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref12
ref56
ref14
bishop (ref31) 2012
ref52
guha (ref26) 2019
ref10
myronenko (ref63) 2018
bakas (ref61) 2018
of north america (ref58) 2018
chang (ref18) 2019
loshchilov (ref60) 2016
ye (ref59) 2020
jeong (ref19) 2018
ref51
lamontagne (ref69) 2018; 14
zhao (ref6) 2018
ref45
peng (ref55) 2020
ref47
ref41
li (ref5) 2018
ref44
zagoruyko (ref43) 2017
smith (ref3) 2017
hinton (ref33) 2015
zhu (ref40) 2018
asif (ref35) 2019
shin (ref25) 2020
romero (ref42) 2015
blitzer (ref53) 2007
zhou (ref24) 2020
karimireddy (ref8) 2020
wang (ref7) 2020
mcmahan (ref2) 2017
ref37
song (ref39) 2018
zbontar (ref65) 2018
ref36
li (ref13) 2019
ref30
ref32
ref1
shazeer (ref34) 2017
ref38
sheller (ref9) 2018
bakas (ref67) 2020
ronneberger (ref70) 2015
zhu (ref15) 2019
park (ref48) 2020
li (ref11) 2020
ref68
geiping (ref16) 2020
ref23
ref64
ref22
papernot (ref27) 2016
ref21
lin (ref20) 2020
london (ref66) 2022
ref28
planche (ref54) 2020
ref29
li (ref17) 2019
furlanello (ref49) 2018
harry hsu (ref4) 2019
ref62
liu (ref50) 2019
huang (ref46) 2017
References_xml – start-page: 1
  year: 2019
  ident: ref15
  article-title: Deep leakage from gradients
  publication-title: Proc NeurIPS
– volume: 14
  start-page: 1097p
  year: 2018
  ident: ref69
  article-title: OASIS-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer's disease
  publication-title: Alzheimer's & Dementia
– ident: ref51
  doi: 10.1109/CVPR.2018.00960
– start-page: 1
  year: 2020
  ident: ref11
  article-title: Fair resource allocation in federated learning
  publication-title: Proc ICLR
– start-page: 1
  year: 2020
  ident: ref55
  article-title: Federated adversarial domain adaptation
  publication-title: Proc ICLR
– year: 2019
  ident: ref4
  article-title: Measuring the effects of non-identical data distribution for federated visual classification
  publication-title: arXiv 1909 06335
– year: 2018
  ident: ref5
  article-title: Federated optimization in heterogeneous networks
  publication-title: arXiv 1812 06127
– year: 2018
  ident: ref6
  article-title: Federated learning with non-IID data
  publication-title: arXiv 1806 00582
– ident: ref12
  doi: 10.1007/978-3-030-58607-2_5
– start-page: 7517
  year: 2018
  ident: ref40
  article-title: Knowledge distillation by on-the-fly native ensemble
  publication-title: Proc NeurIPS
– year: 2018
  ident: ref65
  article-title: fastMRI: An open dataset and benchmarks for accelerated MRI
  publication-title: arXiv 1811 08839
– start-page: 133
  year: 2019
  ident: ref13
  article-title: Privacy-preserving federated brain tumour segmentation
  publication-title: Proc Int Workshop Mach Learn Med Imag
– ident: ref36
  doi: 10.1007/978-3-030-58558-7_15
– start-page: 1
  year: 2020
  ident: ref20
  article-title: Ensemble distillation for robust model fusion in federated learning
  publication-title: Proc NeurIPS
– year: 2020
  ident: ref54
  publication-title: Bridging the realism gap for cad-based visual recognition
– start-page: 92
  year: 2018
  ident: ref9
  article-title: Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation
  publication-title: Proc MICCAI BrainLesion Workshop
– year: 2019
  ident: ref18
  article-title: Cronus: Robust and heterogeneous collaborative learning with black-box knowledge transfer
  publication-title: arXiv 1912 11279
– ident: ref10
  doi: 10.1016/j.media.2021.101992
– ident: ref21
  doi: 10.1109/ICCV48922.2021.01480
– ident: ref38
  doi: 10.1145/3097983.3098135
– ident: ref52
  doi: 10.1007/s10994-009-5152-4
– ident: ref64
  doi: 10.1109/CVPR46437.2021.00245
– year: 2020
  ident: ref67
  article-title: Brats MICCAI Brain tumor dataset
  publication-title: IEEE Dataport
– ident: ref32
  doi: 10.1162/neco.1991.3.1.79
– ident: ref44
  doi: 10.1109/CVPR.2019.00528
– start-page: 129
  year: 2007
  ident: ref53
  article-title: Learning bounds for domain adaptation
  publication-title: Proc 20th Int Conf Neural Inf Process Syst (NIPS)
– year: 2022
  ident: ref66
  publication-title: The IXI Dataset
– year: 2019
  ident: ref35
  article-title: Ensemble knowledge distillation for learning improved and efficient networks
  publication-title: arXiv 1909 08097
– ident: ref68
  doi: 10.1158/1078-0432.CCR-18-1233
– year: 2020
  ident: ref25
  article-title: XOR mixup: Privacy-preserving data augmentation for one-shot federated learning
  publication-title: arXiv 2006 05148
– ident: ref30
  doi: 10.1162/089976699300016737
– ident: ref22
  doi: 10.1109/ICCV.2017.74
– ident: ref29
  doi: 10.1145/1015330.1015432
– year: 2012
  ident: ref31
  article-title: Bayesian hierarchical mixtures of experts
  publication-title: arXiv 1212 2447
– start-page: 1
  year: 2018
  ident: ref49
  article-title: Born again neural networks
  publication-title: Proc PMLR
– start-page: 234
  year: 2015
  ident: ref70
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Proc MICCAI
– ident: ref57
  doi: 10.1609/aaai.v33i01.3301590
– ident: ref23
  doi: 10.1109/CVPR.2018.00813
– start-page: 1
  year: 2017
  ident: ref43
  article-title: Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer
  publication-title: ICLRE
– ident: ref62
  doi: 10.1109/TMI.2014.2377694
– year: 2019
  ident: ref17
  article-title: FedMD: Heterogenous federated learning via model distillation
  publication-title: arXiv 1910 03581
– start-page: 1
  year: 2020
  ident: ref7
  article-title: Federated learning with matched averaging
  publication-title: Proc ICLR
– year: 2017
  ident: ref46
  article-title: Like what you like: Knowledge distill via neuron selectivity transfer
  publication-title: arXiv 1707 01219
– start-page: 4424
  year: 2017
  ident: ref3
  article-title: Federated multi-task learning
  publication-title: Proc NeurIPS
– year: 2018
  ident: ref19
  article-title: Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data
  publication-title: arXiv 1811 11479
– ident: ref47
  doi: 10.1109/CVPR42600.2020.00241
– year: 2016
  ident: ref27
  article-title: Semi-supervised knowledge transfer for deep learning from private training data
  publication-title: arXiv 1610 05755
– ident: ref1
  doi: 10.1109/MNET.2018.1700202
– year: 2019
  ident: ref26
  article-title: One-shot federated learning
  publication-title: arXiv 1902 11175
– year: 2018
  ident: ref61
  article-title: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge
  publication-title: arXiv 1811 02629
– start-page: 1832
  year: 2018
  ident: ref39
  article-title: Collaborative learning for deep neural networks
  publication-title: Proc NeurIPS
– year: 2015
  ident: ref33
  article-title: Distilling the knowledge in a neural network
  publication-title: ArXiv 1503 02531
– start-page: 1
  year: 2019
  ident: ref50
  article-title: Knowledge flow: Improve upon your teachers
  publication-title: ICLRE
– start-page: 1
  year: 2015
  ident: ref42
  article-title: FitNets: Hints for thin deep nets
  publication-title: Proc ICLR
– ident: ref37
  doi: 10.1109/CVPR.2019.00128
– start-page: 311
  year: 2018
  ident: ref63
  article-title: 3D MRI brain tumor segmentation using autoencoder regularization
  publication-title: Proc MICCAI BrainLesion Workshop
– ident: ref28
  doi: 10.1016/S0004-3702(02)00190-X
– start-page: 1
  year: 2020
  ident: ref16
  article-title: Inverting gradients-How easy is it to break privacy in federated learning?
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 1
  year: 2020
  ident: ref48
  article-title: FEED: Feature-level ensemble for knowledge distillation
  publication-title: Proc AAAI
– start-page: 1273
  year: 2017
  ident: ref2
  article-title: Communication-efficient learning of deep networks from decentralized data
  publication-title: Proc 20th Int Conf Artif Intell Statist
– ident: ref56
  doi: 10.1109/CVPR.2017.369
– ident: ref14
  doi: 10.1016/j.media.2020.101765
– year: 2020
  ident: ref24
  article-title: Distilled one-shot federated learning
  publication-title: arXiv 2009 07999
– year: 2016
  ident: ref60
  article-title: SGDR: Stochastic gradient descent with warm restarts
  publication-title: arXiv 1608 03983
– ident: ref41
  doi: 10.1109/CVPR42600.2020.01103
– ident: ref45
  doi: 10.1109/CVPR.2017.754
– year: 2020
  ident: ref59
  article-title: Weakly supervised lesion localization with probabilistic-cam pooling
  publication-title: arXiv 2005 14480
– start-page: 1
  year: 2017
  ident: ref34
  article-title: Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
  publication-title: Proc ICLR
– start-page: 5132
  year: 2020
  ident: ref8
  article-title: SCAFFOLD: Stochastic controlled averaging for on-device federated learning
  publication-title: Proc ICML
– year: 2018
  ident: ref58
  publication-title: RSNA Pneumonia Detection Challenge Dataset
SSID ssj0014509
Score 2.550992
Snippet Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2057
SubjectTerms Data models
Distillation
Federated learning
Hospitals
Humans
Image classification
Image processing
Image reconstruction
Image segmentation
Leakage
Machine Learning
Privacy
Risk reduction
Servers
Task analysis
Training
Title Federated Learning With Privacy-Preserving Ensemble Attention Distillation
URI https://ieeexplore.ieee.org/document/9915468
https://www.ncbi.nlm.nih.gov/pubmed/36215346
https://www.proquest.com/docview/2831508082
https://www.proquest.com/docview/2723814596
Volume 42
WOSCitedRecordID wos001022138900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-254X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014509
  issn: 0278-0062
  databaseCode: RIE
  dateStart: 19820101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB_aImIf_Gi1ptYSwRfB9Pb2I9k8Fu2hYksfqt5byO5O7ME1J3e5gv99Z5Jc6IMKvoSQTDZhZ3b3N5nZ3wC8zQTyhp4q0UYJOlR5UvoKE-sqNCUtuL6la_r-Nbu4sNNpfrkF74e9MIjYJp_hCZ-2sfyw8Gv-VTYiLGOo4W3YzrK026s1RAy06dI5JDPGilRuQpIiH12dfyZHUMoTJcn30lyKh6ZtGuqMeu-tRm15lb8jzXbFmTz5v299Co97ZBmfdqbwDLaw3oPde3yDe_DwvI-k78OXCbNIENAMcU-x-jP-MWuu48vl7Lb0vxPOzeB5hK6f1Su8cXOMT5umy46MP_LUMO_y6J7Dt8nZ1YdPSV9XIfFKZ03iXFmJgOMgU1cZ5U2OhCN0IOcLrXGZHzs7Fj5D69Q4BOVSn0kjS-PLigSFegE79aLGlxBb6TwhNKd1SDVa5aTSwuUhaFTBOhnBaNO_he9Jx7n2xbxonQ-RF6ScgpVT9MqJ4N3wxK-OcOMfsvvc8YNc3-cRHG1UWPQjclUQjGLqe0I8EbwZbtNY4gBJWeNiTTJcgY0sKU8jOOhUP7S9sZjDP7_zFTziQvRdIu8R7DTLNb6GB_62ma2Wx2SwU3vcGuwdqcDj6w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9NAEB6VgngceLQUDAWMxAWpbjb78ONYQaMWkqiHAL1Z3t0xREodlDiV-PfM2I7VAyBxsSx7vLZ2Zne_8cx-A_AuEcgbespIGyXoUGZR4UqMUluiKWjBdQ1d09dxMp2ml5fZxQ4c9XthELFJPsNjPm1i-X7pNvyrbEBYxlDDt-A2V87qdmv1MQNt2oQOyZyxIpbboKTIBrPJObmCUh4rSd6X5mI8NHHTYGfce2M9agqs_B1rNmvO6NH_fe1jeNhhy_CkNYYnsIPVHjy4wTi4B3cnXSx9Hz6NmEeCoKYPO5LV7-G3ef0jvFjNrwv3K-LsDJ5J6PpptcYru8DwpK7b_MjwI08OizaT7il8GZ3OPpxFXWWFyCmd1JG1RSk8Dr2MbWmUMxkSktCe3C9MjU3c0KZD4RJMrRp6r2zsEmlkYVxRkqBQB7BbLSt8DmEqrSOMZrX2scZUWam0sJn3GpVPrQxgsO3f3HW041z9YpE37ofIclJOzsrJO-UE8L5_4mdLufEP2X3u-F6u6_MADrcqzLsxuc4JSDH5PWGeAN72t2k0cYikqHC5IRmuwUaWlMUBPGtV37e9tZgXf37nG7h3NpuM8_H59PNLuM9l6du03kPYrVcbfAV33HU9X69eN2b7G1Jk5kw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Federated+Learning+With+Privacy-Preserving+Ensemble+Attention+Distillation&rft.jtitle=IEEE+transactions+on+medical+imaging&rft.au=Gong%2C+Xuan&rft.au=Song%2C+Liangchen&rft.au=Vedula%2C+Rishi&rft.au=Sharma%2C+Abhishek&rft.date=2023-07-01&rft.issn=1558-254X&rft.eissn=1558-254X&rft.volume=42&rft.issue=7&rft.spage=2057&rft_id=info:doi/10.1109%2FTMI.2022.3213244&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0062&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0062&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0062&client=summon