Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach Article Swipe
Wenkang Ji
,
Jian Zhou
,
Fu Xiao
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.17260
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.17260
Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients. Existing solutions primarily address these challenges by incorporating wireless resource optimization strategies, often focusing on uplink resource allocation across clients under the assumption of homogeneous client-server network standards. However, these approaches overlooked the fact that mobile clients may connect to the server via diverse network standards (e.g., 4G, 5G, Wi-Fi) with customized configurations, limiting the flexibility of server-side modifications and restricting applicability in real-world commercial networks. This paper presents a novel theoretical analysis about how transmission failures in unreliable networks distort the effective label distributions of local samples, causing deviations from the global data distribution and introducing convergence bias in FL. Our analysis reveals that a carefully designed client selection strategy can mitigate biases induced by network unreliability and data heterogeneity. Motivated by this insight, we propose FedCote, a client selection approach that optimizes client selection probabilities without relying on wireless resource scheduling. Experimental results demonstrate the robustness of FedCote in DNN-based classification tasks under unreliable networks with frequent transmission failures.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2502.17260
- https://arxiv.org/pdf/2502.17260
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416679292
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416679292Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2502.17260Digital Object Identifier
- Title
-
Robust Federated Learning in Unreliable Wireless Networks: A Client Selection ApproachWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-24Full publication date if available
- Authors
-
Wenkang Ji, Jian Zhou, Fu XiaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2502.17260Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2502.17260Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2502.17260Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416679292 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2502.17260 |
| ids.doi | https://doi.org/10.48550/arxiv.2502.17260 |
| ids.openalex | https://openalex.org/W4416679292 |
| fwci | |
| type | preprint |
| title | Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2502.17260 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2502.17260 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2502.17260 |
| locations[1].id | doi:10.48550/arxiv.2502.17260 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2502.17260 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5049044867 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Wenkang Ji |
| authorships[0].author_position | middle |
| authorships[0].raw_author_name | Ji, Wenkai |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5082547849 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-1864-3894 |
| authorships[1].author.display_name | Jian Zhou |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Zhou, Jian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100602821 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1815-2793 |
| authorships[2].author.display_name | Fu Xiao |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xiao, Fu |
| authorships[2].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2502.17260 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T20:31:18.283634 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2502.17260 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2502.17260 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2502.17260 |
| primary_location.id | pmh:oai:arXiv.org:2502.17260 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2502.17260 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2502.17260 |
| publication_date | 2025-02-24 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 107, 143, 166 |
| abstract_inverted_index.as | 5 |
| abstract_inverted_index.at | 17 |
| abstract_inverted_index.be | 25 |
| abstract_inverted_index.by | 28, 44, 153, 160 |
| abstract_inverted_index.in | 100, 115, 137, 188 |
| abstract_inverted_index.of | 61, 94, 123, 186 |
| abstract_inverted_index.on | 52, 177 |
| abstract_inverted_index.to | 77 |
| abstract_inverted_index.we | 163 |
| abstract_inverted_index.4G, | 85 |
| abstract_inverted_index.5G, | 86 |
| abstract_inverted_index.FL. | 138 |
| abstract_inverted_index.Our | 139 |
| abstract_inverted_index.and | 32, 97, 133, 156 |
| abstract_inverted_index.but | 21 |
| abstract_inverted_index.can | 24, 149 |
| abstract_inverted_index.for | 11 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.how | 112 |
| abstract_inverted_index.its | 22 |
| abstract_inverted_index.may | 75 |
| abstract_inverted_index.the | 18, 59, 70, 78, 92, 119, 129, 184 |
| abstract_inverted_index.via | 80 |
| abstract_inverted_index.(FL) | 2 |
| abstract_inverted_index.This | 104 |
| abstract_inverted_index.bias | 136 |
| abstract_inverted_index.data | 34, 131, 157 |
| abstract_inverted_index.deep | 13 |
| abstract_inverted_index.fact | 71 |
| abstract_inverted_index.from | 128 |
| abstract_inverted_index.that | 72, 142, 170 |
| abstract_inverted_index.this | 161 |
| abstract_inverted_index.with | 88, 195 |
| abstract_inverted_index.about | 111 |
| abstract_inverted_index.among | 36 |
| abstract_inverted_index.edge, | 20 |
| abstract_inverted_index.label | 121 |
| abstract_inverted_index.local | 124 |
| abstract_inverted_index.novel | 108 |
| abstract_inverted_index.often | 50 |
| abstract_inverted_index.paper | 105 |
| abstract_inverted_index.tasks | 191 |
| abstract_inverted_index.these | 42, 67 |
| abstract_inverted_index.under | 58, 192 |
| abstract_inverted_index.(DNNs) | 16 |
| abstract_inverted_index.(e.g., | 84 |
| abstract_inverted_index.Wi-Fi) | 87 |
| abstract_inverted_index.across | 56 |
| abstract_inverted_index.biases | 151 |
| abstract_inverted_index.client | 146, 167, 172 |
| abstract_inverted_index.global | 130 |
| abstract_inverted_index.mobile | 73 |
| abstract_inverted_index.neural | 14 |
| abstract_inverted_index.server | 79 |
| abstract_inverted_index.uplink | 53 |
| abstract_inverted_index.FedCote | 187 |
| abstract_inverted_index.address | 41 |
| abstract_inverted_index.causing | 126 |
| abstract_inverted_index.clients | 57, 74 |
| abstract_inverted_index.connect | 76 |
| abstract_inverted_index.distort | 118 |
| abstract_inverted_index.diverse | 81 |
| abstract_inverted_index.emerged | 4 |
| abstract_inverted_index.induced | 152 |
| abstract_inverted_index.network | 64, 82, 154 |
| abstract_inverted_index.propose | 164 |
| abstract_inverted_index.relying | 176 |
| abstract_inverted_index.results | 182 |
| abstract_inverted_index.reveals | 141 |
| abstract_inverted_index.without | 175 |
| abstract_inverted_index.Existing | 38 |
| abstract_inverted_index.FedCote, | 165 |
| abstract_inverted_index.However, | 66 |
| abstract_inverted_index.analysis | 110, 140 |
| abstract_inverted_index.approach | 169 |
| abstract_inverted_index.clients. | 37 |
| abstract_inverted_index.designed | 145 |
| abstract_inverted_index.failures | 114 |
| abstract_inverted_index.focusing | 51 |
| abstract_inverted_index.frequent | 196 |
| abstract_inverted_index.hindered | 27 |
| abstract_inverted_index.inherent | 33 |
| abstract_inverted_index.insight, | 162 |
| abstract_inverted_index.learning | 1, 9 |
| abstract_inverted_index.limiting | 91 |
| abstract_inverted_index.mitigate | 150 |
| abstract_inverted_index.networks | 15, 117, 194 |
| abstract_inverted_index.paradigm | 10 |
| abstract_inverted_index.presents | 106 |
| abstract_inverted_index.resource | 47, 54, 179 |
| abstract_inverted_index.samples, | 125 |
| abstract_inverted_index.severely | 26 |
| abstract_inverted_index.strategy | 148 |
| abstract_inverted_index.training | 12 |
| abstract_inverted_index.wireless | 19, 30, 46, 178 |
| abstract_inverted_index.DNN-based | 189 |
| abstract_inverted_index.Federated | 0 |
| abstract_inverted_index.Motivated | 159 |
| abstract_inverted_index.carefully | 144 |
| abstract_inverted_index.effective | 120 |
| abstract_inverted_index.failures. | 198 |
| abstract_inverted_index.networks. | 103 |
| abstract_inverted_index.optimizes | 171 |
| abstract_inverted_index.primarily | 40 |
| abstract_inverted_index.promising | 7 |
| abstract_inverted_index.selection | 147, 168, 173 |
| abstract_inverted_index.solutions | 39 |
| abstract_inverted_index.standards | 83 |
| abstract_inverted_index.allocation | 55 |
| abstract_inverted_index.approaches | 68 |
| abstract_inverted_index.assumption | 60 |
| abstract_inverted_index.challenges | 43 |
| abstract_inverted_index.commercial | 102 |
| abstract_inverted_index.customized | 89 |
| abstract_inverted_index.deviations | 127 |
| abstract_inverted_index.overlooked | 69 |
| abstract_inverted_index.real-world | 101 |
| abstract_inverted_index.robustness | 185 |
| abstract_inverted_index.standards. | 65 |
| abstract_inverted_index.unreliable | 29, 116, 193 |
| abstract_inverted_index.convergence | 135 |
| abstract_inverted_index.demonstrate | 183 |
| abstract_inverted_index.distributed | 8 |
| abstract_inverted_index.flexibility | 93 |
| abstract_inverted_index.homogeneous | 62 |
| abstract_inverted_index.introducing | 134 |
| abstract_inverted_index.performance | 23 |
| abstract_inverted_index.restricting | 98 |
| abstract_inverted_index.scheduling. | 180 |
| abstract_inverted_index.server-side | 95 |
| abstract_inverted_index.strategies, | 49 |
| abstract_inverted_index.theoretical | 109 |
| abstract_inverted_index.Experimental | 181 |
| abstract_inverted_index.distribution | 132 |
| abstract_inverted_index.optimization | 48 |
| abstract_inverted_index.transmission | 31, 113, 197 |
| abstract_inverted_index.applicability | 99 |
| abstract_inverted_index.client-server | 63 |
| abstract_inverted_index.distributions | 122 |
| abstract_inverted_index.heterogeneity | 35 |
| abstract_inverted_index.incorporating | 45 |
| abstract_inverted_index.modifications | 96 |
| abstract_inverted_index.probabilities | 174 |
| abstract_inverted_index.unreliability | 155 |
| abstract_inverted_index.classification | 190 |
| abstract_inverted_index.heterogeneity. | 158 |
| abstract_inverted_index.configurations, | 90 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |