Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems

The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learn...

Full description

Saved in:
Bibliographic Details
Published in:IEEE Communications surveys and tutorials Vol. 23; no. 2; pp. 1342 - 1397
Main Authors: Wahab, Omar Abdel, Mourad, Azzam, Otrok, Hadi, Taleb, Tarik
Format: Journal Article
Language:English
Published: IEEE 01.01.2021
Subjects:
ISSN:2373-745X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called Federated Learning . The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.
AbstractList The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called Federated Learning . The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.
Author Mourad, Azzam
Otrok, Hadi
Wahab, Omar Abdel
Taleb, Tarik
Author_xml – sequence: 1
  givenname: Omar Abdel
  orcidid: 0000-0002-3991-4673
  surname: Wahab
  fullname: Wahab, Omar Abdel
  email: omar.abdulwahab@uqo.ca
  organization: Department of Computer Science and Engineering, Université du Québec en Outaouais, Gatineau, Canada
– sequence: 2
  givenname: Azzam
  orcidid: 0000-0001-9434-5322
  surname: Mourad
  fullname: Mourad, Azzam
  email: azzam.mourad@lau.edu.lb
  organization: Department of Mathematics and Computer Science, Lebanese American University, Beirut, Lebanon
– sequence: 3
  givenname: Hadi
  orcidid: 0000-0002-9574-5384
  surname: Otrok
  fullname: Otrok, Hadi
  email: hadi.otrok@ku.ac.ae
  organization: Department of EECS, Center on Cyber-Physical Systems, Khalifa University of Science and Technology, Abu Dhabi, UAE
– sequence: 4
  givenname: Tarik
  orcidid: 0000-0003-1119-1239
  surname: Taleb
  fullname: Taleb, Tarik
  email: tarik.taleb@aalto.fi
  organization: Department of Communications and Networking, Aalto University, Espoo, Finland
BookMark eNotjU1OwzAUhC0EEqVwAdj4AE2x_fLTsEMpBaSULlokdtWL8wqGxEG2U9RbcGQKdDXS6Ptmztix7SwxdinFWEqRXxeL-XI1VkLJMYhkkmRwxAYKMoiyOHk5ZWfevwsRqzgXA_Y9o5ocBqr5HPWbscRLQmeNfb3hy95taTfi874JJippSw0vGvTebIzGYDo74lPyxmHVEC-cCeQMcrQ1n_Whd8SnxpH-BT03lhdd2_b2oP5hTxS-Ovexf-PLnQ_U-nN2ssHG08Uhh-x5drcqHqJycf9Y3JaRBshDhDKvABDzOk51RZjIjapSBKwlKBmj0EpQCpihzmgCMFGVToSiNI2TfZnCkF397xoiWn8606LbrXNIlACAH8QdZrU
CitedBy_id crossref_primary_10_1016_j_cose_2023_103343
crossref_primary_10_1109_JIOT_2021_3100755
crossref_primary_10_1016_j_ins_2022_11_126
crossref_primary_10_1007_s00607_022_01078_1
crossref_primary_10_1109_JIOT_2022_3218755
crossref_primary_10_1016_j_comcom_2025_108261
crossref_primary_10_3390_electronics12122612
crossref_primary_10_3390_s21175805
crossref_primary_10_1109_ACCESS_2023_3315771
crossref_primary_10_1016_j_ins_2022_12_045
crossref_primary_10_1002_ett_4458
crossref_primary_10_1007_s13042_024_02436_5
crossref_primary_10_3390_app12189124
crossref_primary_10_1016_j_future_2024_04_051
crossref_primary_10_7717_peerj_cs_2360
crossref_primary_10_1016_j_jprocont_2022_06_011
crossref_primary_10_1016_j_comnet_2021_108668
crossref_primary_10_1155_2022_4268589
crossref_primary_10_3390_s22020450
crossref_primary_10_1109_TNSM_2024_3520109
crossref_primary_10_1109_ACCESS_2023_3251571
crossref_primary_10_1016_j_vehcom_2021_100396
crossref_primary_10_1016_j_pmcj_2024_101948
crossref_primary_10_1109_ACCESS_2025_3595270
crossref_primary_10_1007_s11277_024_11372_0
crossref_primary_10_1109_TWC_2024_3466177
crossref_primary_10_1109_COMST_2023_3316615
crossref_primary_10_1109_TNSM_2024_3514212
crossref_primary_10_1016_j_jpdc_2024_104918
crossref_primary_10_1016_j_measurement_2025_117677
crossref_primary_10_1109_MCOMSTD_0004_2200076
crossref_primary_10_1016_j_ins_2022_04_027
crossref_primary_10_1016_j_ipm_2022_103150
crossref_primary_10_1109_MWC_005_00334
crossref_primary_10_1109_TGCN_2022_3186898
crossref_primary_10_1109_TSC_2024_3376259
crossref_primary_10_3390_app13095270
crossref_primary_10_1109_TMC_2023_3321467
crossref_primary_10_1109_TII_2022_3223234
crossref_primary_10_1038_s41598_023_47078_9
crossref_primary_10_1109_ACCESS_2025_3553419
crossref_primary_10_1007_s10586_022_03644_w
crossref_primary_10_1109_JIOT_2022_3203249
crossref_primary_10_1109_TNSE_2023_3260566
crossref_primary_10_1109_TNSM_2022_3216326
crossref_primary_10_1002_ett_70101
crossref_primary_10_1016_j_comcom_2025_108275
crossref_primary_10_1016_j_future_2022_07_010
crossref_primary_10_1109_TNSM_2023_3276594
crossref_primary_10_1109_TWC_2023_3273312
crossref_primary_10_1109_TKDE_2023_3332770
crossref_primary_10_1109_TNSM_2023_3336067
crossref_primary_10_1109_ACCESS_2021_3104117
crossref_primary_10_3390_s25175526
crossref_primary_10_1109_TNSM_2023_3281133
crossref_primary_10_1109_ACCESS_2024_3507695
crossref_primary_10_1016_j_jmsy_2021_09_009
crossref_primary_10_1016_j_rineng_2024_103295
crossref_primary_10_1109_ACCESS_2023_3267964
crossref_primary_10_1109_MNET_131_2200394
crossref_primary_10_1038_s41598_024_56115_0
crossref_primary_10_1109_COMST_2023_3243918
crossref_primary_10_1109_ACCESS_2024_3483455
crossref_primary_10_1016_j_comnet_2022_109048
crossref_primary_10_1145_3548686
crossref_primary_10_1016_j_bspc_2024_107107
crossref_primary_10_1109_TMC_2024_3449129
crossref_primary_10_1016_j_comcom_2022_09_012
crossref_primary_10_1109_TMC_2021_3085979
crossref_primary_10_1016_j_iot_2023_100694
crossref_primary_10_1109_JIOT_2021_3068056
crossref_primary_10_1007_s13042_024_02453_4
crossref_primary_10_1145_3664650
crossref_primary_10_1007_s11042_025_20815_0
crossref_primary_10_1109_IOTM_001_2100136
crossref_primary_10_1109_ACCESS_2021_3118642
crossref_primary_10_1109_TWC_2024_3471906
crossref_primary_10_1145_3673237
crossref_primary_10_1109_ACCESS_2022_3206020
crossref_primary_10_1109_ACCESS_2024_3449416
crossref_primary_10_1109_JIOT_2024_3363443
crossref_primary_10_1145_3625558
crossref_primary_10_3390_electronics12122703
crossref_primary_10_1109_ACCESS_2024_3424934
crossref_primary_10_32604_cmc_2023_043684
crossref_primary_10_1007_s00607_024_01356_0
crossref_primary_10_1016_j_neunet_2025_107135
crossref_primary_10_1109_TWC_2022_3188502
crossref_primary_10_2478_bipie_2022_0019
crossref_primary_10_1109_TNSM_2021_3128160
crossref_primary_10_1109_COMST_2023_3282264
crossref_primary_10_1016_j_cose_2024_104097
crossref_primary_10_1109_JIOT_2023_3327316
crossref_primary_10_1016_j_phycom_2024_102305
crossref_primary_10_1016_j_engappai_2024_108128
crossref_primary_10_1109_LCOMM_2022_3167094
crossref_primary_10_1631_FITEE_2300122
crossref_primary_10_1109_JIOT_2022_3157299
crossref_primary_10_1109_JIOT_2023_3304790
crossref_primary_10_1109_TWC_2023_3270908
crossref_primary_10_1016_j_comnet_2023_109581
crossref_primary_10_1016_j_future_2022_06_006
crossref_primary_10_1016_j_eswa_2025_128600
crossref_primary_10_1109_MNET_121_2200099
crossref_primary_10_1109_JIOT_2022_3188556
crossref_primary_10_1109_TITS_2024_3488497
crossref_primary_10_1016_j_measen_2024_101271
crossref_primary_10_3390_ai5030051
crossref_primary_10_1109_TNSM_2024_3508268
crossref_primary_10_1016_j_cosrev_2023_100595
crossref_primary_10_32604_cmc_2023_035720
crossref_primary_10_1109_ACCESS_2025_3593953
crossref_primary_10_1016_j_comnet_2023_109576
crossref_primary_10_1109_TNSM_2023_3270168
crossref_primary_10_1109_COMST_2023_3300664
crossref_primary_10_3390_fi15120400
crossref_primary_10_1016_j_adhoc_2024_103637
crossref_primary_10_1016_j_comcom_2025_108112
crossref_primary_10_1109_JSYST_2024_3450883
crossref_primary_10_1109_TKDE_2024_3382726
crossref_primary_10_1109_TSC_2023_3246988
crossref_primary_10_3390_jmse12061034
crossref_primary_10_1109_JIOT_2022_3214211
crossref_primary_10_1016_j_knosys_2023_110273
crossref_primary_10_1007_s12243_025_01089_x
crossref_primary_10_3390_s25175286
crossref_primary_10_1016_j_eswa_2025_129146
crossref_primary_10_1145_3678182
crossref_primary_10_1016_j_ejor_2023_12_013
crossref_primary_10_32604_cmc_2024_048431
crossref_primary_10_1109_ACCESS_2023_3235389
crossref_primary_10_1109_ACCESS_2024_3384460
crossref_primary_10_1109_JIOT_2023_3241318
crossref_primary_10_1109_TSC_2024_3489437
crossref_primary_10_1109_TVT_2022_3229277
crossref_primary_10_1109_ACCESS_2025_3580176
crossref_primary_10_1109_TNSM_2023_3278937
crossref_primary_10_1109_JSAC_2021_3118346
crossref_primary_10_3390_s25030948
crossref_primary_10_1145_3582270
crossref_primary_10_1145_3639825
crossref_primary_10_1109_ACCESS_2024_3516657
crossref_primary_10_1109_COMST_2024_3392642
crossref_primary_10_1109_TCSS_2023_3259431
crossref_primary_10_1145_3659099
crossref_primary_10_1016_j_future_2023_07_018
crossref_primary_10_1177_15501329221092932
crossref_primary_10_1016_j_future_2022_05_003
crossref_primary_10_1016_j_comnet_2024_110192
crossref_primary_10_1002_widm_1514
crossref_primary_10_1109_TDSC_2023_3264697
crossref_primary_10_1109_TNSM_2022_3208522
crossref_primary_10_1109_JSYST_2023_3243694
crossref_primary_10_3390_s25082368
crossref_primary_10_1109_TWC_2024_3522956
crossref_primary_10_1109_TETCI_2023_3251404
crossref_primary_10_1109_COMST_2021_3094993
crossref_primary_10_1016_j_bspc_2024_106039
crossref_primary_10_1109_ACCESS_2021_3111783
crossref_primary_10_1109_TII_2024_3485720
crossref_primary_10_1109_TNET_2024_3364161
crossref_primary_10_32604_cmes_2024_056500
crossref_primary_10_1109_JSTSP_2022_3156756
crossref_primary_10_1109_TNSE_2024_3398795
crossref_primary_10_1007_s10489_022_04431_1
crossref_primary_10_7717_peerj_cs_1657
crossref_primary_10_1016_j_ins_2024_121035
crossref_primary_10_1109_JIOT_2025_3561722
crossref_primary_10_1109_TNET_2024_3365815
crossref_primary_10_1016_j_comnet_2024_110663
crossref_primary_10_1007_s10796_022_10307_z
crossref_primary_10_1109_COMST_2024_3400121
crossref_primary_10_1016_j_neucom_2022_11_011
crossref_primary_10_1007_s10462_024_10796_1
crossref_primary_10_3390_s23083984
crossref_primary_10_1109_JIOT_2023_3325443
crossref_primary_10_1109_MCOM_005_210108
crossref_primary_10_3390_technologies11030076
crossref_primary_10_1109_TII_2021_3117861
crossref_primary_10_1155_2021_8414503
crossref_primary_10_1109_ACCESS_2024_3350777
crossref_primary_10_1155_2022_2235042
crossref_primary_10_1109_LCOMM_2023_3312793
crossref_primary_10_1109_TVT_2023_3328988
crossref_primary_10_1109_JIOT_2024_3379363
crossref_primary_10_1109_TNSM_2023_3282740
crossref_primary_10_1016_j_eswa_2025_126592
crossref_primary_10_3390_s22093317
crossref_primary_10_1002_ett_4762
crossref_primary_10_1109_LCOMM_2023_3348163
crossref_primary_10_1007_s00500_021_06496_5
crossref_primary_10_1177_21582440231173652
crossref_primary_10_1016_j_inffus_2025_103129
crossref_primary_10_1109_TBDATA_2022_3177222
crossref_primary_10_1007_s10489_024_05956_3
crossref_primary_10_1109_JIOT_2022_3218315
crossref_primary_10_1109_JSTSP_2022_3224597
crossref_primary_10_3390_network5010001
crossref_primary_10_1016_j_comnet_2023_110044
crossref_primary_10_1109_ACCESS_2021_3101871
crossref_primary_10_1177_21582440241237050
crossref_primary_10_1007_s12083_024_01840_6
crossref_primary_10_1109_JIOT_2023_3265564
crossref_primary_10_1109_TIFS_2022_3181848
crossref_primary_10_1109_JSTSP_2023_3239189
crossref_primary_10_1016_j_comnet_2025_111139
crossref_primary_10_1016_j_inffus_2023_102141
crossref_primary_10_1016_j_ins_2023_119976
crossref_primary_10_1109_TNSE_2023_3311024
crossref_primary_10_1016_j_adhoc_2024_103462
crossref_primary_10_1016_j_comnet_2023_109712
crossref_primary_10_1016_j_jnca_2024_103987
crossref_primary_10_1155_2022_9369543
crossref_primary_10_1109_TIM_2023_3341116
crossref_primary_10_32604_iasc_2023_039255
crossref_primary_10_1002_widm_1443
crossref_primary_10_1016_j_ins_2024_120330
crossref_primary_10_1007_s11227_025_07133_w
crossref_primary_10_1109_ACCESS_2022_3229044
crossref_primary_10_1049_cth2_12761
crossref_primary_10_1016_j_cose_2024_103707
crossref_primary_10_1109_MNET_117_2100730
crossref_primary_10_1109_TCAD_2021_3110743
crossref_primary_10_3390_bdcc9040085
crossref_primary_10_1145_3718363
crossref_primary_10_1109_JSTQE_2022_3170150
crossref_primary_10_1016_j_compeleceng_2024_109812
crossref_primary_10_32604_cmc_2024_051307
crossref_primary_10_1145_3731596
crossref_primary_10_1145_3570953
crossref_primary_10_3390_electronics12010158
crossref_primary_10_3390_technologies11050121
crossref_primary_10_1109_JIOT_2025_3530265
crossref_primary_10_1016_j_procs_2024_04_279
crossref_primary_10_1155_2022_6216423
crossref_primary_10_1109_JIOT_2023_3283853
crossref_primary_10_1016_j_iot_2024_101206
crossref_primary_10_1109_JIOT_2023_3283855
crossref_primary_10_1109_JIOT_2022_3167005
crossref_primary_10_3390_machines12100701
crossref_primary_10_1109_TVT_2024_3369942
crossref_primary_10_1007_s11432_024_4205_8
crossref_primary_10_1109_TITS_2023_3273167
crossref_primary_10_1145_3687124
crossref_primary_10_1109_COMST_2023_3317242
crossref_primary_10_1109_LWC_2022_3151873
crossref_primary_10_1016_j_enbuild_2024_114871
crossref_primary_10_1109_JIOT_2023_3338275
crossref_primary_10_1109_TNSM_2023_3273396
crossref_primary_10_1016_j_jairtraman_2024_102693
crossref_primary_10_1109_TNNLS_2024_3362974
crossref_primary_10_1109_MCE_2021_3117232
crossref_primary_10_1109_TWC_2022_3225812
crossref_primary_10_1109_MNET_121_2100172
crossref_primary_10_1109_TVT_2022_3211005
crossref_primary_10_1109_ACCESS_2023_3263564
ContentType Journal Article
DBID 97E
RIA
RIE
DOI 10.1109/COMST.2021.3058573
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2373-745X
EndPage 1397
ExternalDocumentID 9352033
Genre orig-research
GrantInformation_xml – fundername: Academy of Finland 6Genesis Project
  grantid: 318927
  funderid: 10.13039/501100002341
– fundername: Université du Québec en Outaouais (UQO)
  funderid: 10.13039/100012376
– fundername: Natural Sciences and Engineering Research Council of Canada (NSERC)
  grantid: RGPIN-2020-04707
  funderid: 10.13039/501100000038
– fundername: Khalifa University of Science, Technology and Research (KUSTAR)
– fundername: Academy of Finland CSN Project
  grantid: 311654
  funderid: 10.13039/501100002341
– fundername: European Union’s Horizon 2020 Research and Innovation Program
  grantid: 101016509 (Project CHARITY)
– fundername: Lebanese American University
  funderid: 10.13039/100010340
GroupedDBID 0R~
29I
2WC
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
AZLTO
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
EJD
HZ~
IES
IFIPE
IFJZH
IPLJI
JAVBF
LAI
O9-
OCL
P2P
RIA
RIE
RNS
ID FETCH-LOGICAL-c339t-a19b33aa9d46cbea51f2b6a3ad13214a0c20e63a7ac7e83382bc502e6645a7a63
IEDL.DBID RIE
ISICitedReferencesCount 330
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000654905700021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:51:12 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c339t-a19b33aa9d46cbea51f2b6a3ad13214a0c20e63a7ac7e83382bc502e6645a7a63
ORCID 0000-0002-3991-4673
0000-0002-9574-5384
0000-0001-9434-5322
0000-0003-1119-1239
OpenAccessLink https://aaltodoc.aalto.fi/handle/123456789/107753
PageCount 56
ParticipantIDs ieee_primary_9352033
PublicationCentury 2000
PublicationDate 2021-01-01
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – month: 01
  year: 2021
  text: 2021-01-01
  day: 01
PublicationDecade 2020
PublicationTitle IEEE Communications surveys and tutorials
PublicationTitleAbbrev COMST
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0042490
Score 2.7104795
Snippet The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved...
SourceID ieee
SourceType Publisher
StartPage 1342
SubjectTerms Cloud computing
Collaborative work
communication and networking systems
Data models
Federated learning
federated learning tutorial
Machine learning
multi-level classification
security
Servers
statistical challenges
Training
transfer learning
Tutorials
Title Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems
URI https://ieeexplore.ieee.org/document/9352033
Volume 23
WOSCitedRecordID wos000654905700021&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA7b8KAHf03xNzl4XLc2aZvGmwyLh20Km7LbSJNX2aWTug38L_yTfUk7meDFWwmBQN4jeV_6vu8j5FYiQBN5oD2mBQIUpnJPCqM8LBWMVFFmcif2_DoQo1EyncrnBun8cGEAwDWfQdd-un_5ZqFX9qmsJ7Fa8DlvkqYQccXV2py6IcIIf0OK8WWv_zQcTxD-saCLGZ1E1hd9yz7F3R7pwf_WPST7dZVI76uwHpEGFMdkb0s7sE2-UisDgZWioUPXEAm01kp9u6PjVbmGzw519FpvYBuDqLO_tI1BLhYdiohzXlriFLV2BzYRqSoMTZ3ICK2PQsxJOi_oLxqJmzaq2sdxNVqLnp-Ql_Rh0n_0ansFT3Mul54KZMa5UtKEsc5ARUHOslhxZQLrXqR8zXyIuRJKC0gQyrJMRz6DOA4jHIz5KWkViwLOCNUY2EQaCQguwwS0lBnOzjWEPuiQBeekbXd19l4paMzqDb34e_iS7NrAVQ8dV6S1LFdwTXb0ejn_KG9c2L8BcRiyLg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFA1zCuqD3-K3efBx3dKkX_FNhmViV4VN2dtIk1vZSyd1G_gv_MkmaScTfPGthEAg95Lck95zDkI3XAO0MHelQ2WoAQoVucNDJRxdKigu_EzlVuz5NQnTNBqN-HMDtX64MABgm8-gbT7tv3w1lXPzVNbhulogjK2hdd_zKKnYWstz19NAgixpMYR3uk_9wVADQOq2dU5HvnFGXzFQsfdHvPu_lffQTl0n4rsqsPuoAcUB2l5RDzxEX7ERgtC1osJ92xIJuFZLfbvFg3m5gM8WtgRbJzGtQdgaYJrWIBuNFtaYc1Ia6hQ2hgcmFbEoFI6tzAiuD0OdlXhS4F9EEjstrRrI9Wq4lj0_Qi_x_bDbc2qDBUcyxmeOcHnGmBBceYHMQPhuTrNAMKFc418kiKQEAiZCIUOINJilmfQJhSDwfD0YsGPULKYFnCAsdWgjrjhoeOlFIDnP9OxcgkdAetQ9RYdmV8fvlYbGuN7Qs7-Hr9Fmb9hPxslD-niOtkwQq2ePC9SclXO4RBtyMZt8lFc2Bb4B3dS1dQ
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+Machine+Learning%3A+Survey%2C+Multi-Level+Classification%2C+Desirable+Criteria+and+Future+Directions+in+Communication+and+Networking+Systems&rft.jtitle=IEEE+Communications+surveys+and+tutorials&rft.au=Wahab%2C+Omar+Abdel&rft.au=Mourad%2C+Azzam&rft.au=Otrok%2C+Hadi&rft.au=Taleb%2C+Tarik&rft.date=2021-01-01&rft.pub=IEEE&rft.eissn=2373-745X&rft.volume=23&rft.issue=2&rft.spage=1342&rft.epage=1397&rft_id=info:doi/10.1109%2FCOMST.2021.3058573&rft.externalDocID=9352033