FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning Article Swipe
Divyansh Jhunjhunwala
,
Pranay Sharma
,
Aushim Nagarkatti
,
Gauri Joshi
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2207.14130
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2207.14130
Data-heterogeneous federated learning (FL) systems suffer from two significant sources of convergence error: 1) client drift error caused by performing multiple local optimization steps at clients, and 2) partial client participation error caused by the fact that only a small subset of the edge clients participate in every training round. We find that among these, only the former has received significant attention in the literature. To remedy this, we propose FedVARP, a novel variance reduction algorithm applied at the server that eliminates error due to partial client participation. To do so, the server simply maintains in memory the most recent update for each client and uses these as surrogate updates for the non-participating clients in every round. Further, to alleviate the memory requirement at the server, we propose a novel clustering-based variance reduction algorithm ClusterFedVARP. Unlike previously proposed methods, both FedVARP and ClusterFedVARP do not require additional computation at clients or communication of additional optimization parameters. Through extensive experiments, we show that FedVARP outperforms state-of-the-art methods, and ClusterFedVARP achieves performance comparable to FedVARP with much less memory requirements.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2207.14130
- https://arxiv.org/pdf/2207.14130
- OA Status
- green
- Cited By
- 7
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4288804715
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4288804715Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2207.14130Digital Object Identifier
- Title
-
FedVARP: Tackling the Variance Due to Partial Client Participation in Federated LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-07-28Full publication date if available
- Authors
-
Divyansh Jhunjhunwala, Pranay Sharma, Aushim Nagarkatti, Gauri JoshiList of authors in order
- Landing page
-
https://arxiv.org/abs/2207.14130Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2207.14130Direct 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/2207.14130Direct OA link when available
- Concepts
-
Computer science, Variance (accounting), Enhanced Data Rates for GSM Evolution, Convergence (economics), Reduction (mathematics), Cluster analysis, Machine learning, Artificial intelligence, Accounting, Business, Geometry, Mathematics, Economic growth, EconomicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
7Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4, 2024: 1, 2023: 1, 2022: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4288804715 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2207.14130 |
| ids.doi | https://doi.org/10.48550/arxiv.2207.14130 |
| ids.openalex | https://openalex.org/W4288804715 |
| fwci | |
| type | preprint |
| title | FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10764 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991000294685364 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Privacy-Preserving Technologies in Data |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8385310769081116 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C196083921 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7419954538345337 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7915758 |
| concepts[1].display_name | Variance (accounting) |
| concepts[2].id | https://openalex.org/C162307627 |
| concepts[2].level | 2 |
| concepts[2].score | 0.608741044998169 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q204833 |
| concepts[2].display_name | Enhanced Data Rates for GSM Evolution |
| concepts[3].id | https://openalex.org/C2777303404 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5797315239906311 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q759757 |
| concepts[3].display_name | Convergence (economics) |
| concepts[4].id | https://openalex.org/C111335779 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5272095203399658 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3454686 |
| concepts[4].display_name | Reduction (mathematics) |
| concepts[5].id | https://openalex.org/C73555534 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5271037817001343 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q622825 |
| concepts[5].display_name | Cluster analysis |
| concepts[6].id | https://openalex.org/C119857082 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4009115397930145 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[6].display_name | Machine learning |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3558916449546814 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C121955636 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q4116214 |
| concepts[8].display_name | Accounting |
| concepts[9].id | https://openalex.org/C144133560 |
| concepts[9].level | 0 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[9].display_name | Business |
| concepts[10].id | https://openalex.org/C2524010 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[10].display_name | Geometry |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C50522688 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q189833 |
| concepts[12].display_name | Economic growth |
| concepts[13].id | https://openalex.org/C162324750 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[13].display_name | Economics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8385310769081116 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/variance |
| keywords[1].score | 0.7419954538345337 |
| keywords[1].display_name | Variance (accounting) |
| keywords[2].id | https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution |
| keywords[2].score | 0.608741044998169 |
| keywords[2].display_name | Enhanced Data Rates for GSM Evolution |
| keywords[3].id | https://openalex.org/keywords/convergence |
| keywords[3].score | 0.5797315239906311 |
| keywords[3].display_name | Convergence (economics) |
| keywords[4].id | https://openalex.org/keywords/reduction |
| keywords[4].score | 0.5272095203399658 |
| keywords[4].display_name | Reduction (mathematics) |
| keywords[5].id | https://openalex.org/keywords/cluster-analysis |
| keywords[5].score | 0.5271037817001343 |
| keywords[5].display_name | Cluster analysis |
| keywords[6].id | https://openalex.org/keywords/machine-learning |
| keywords[6].score | 0.4009115397930145 |
| keywords[6].display_name | Machine learning |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.3558916449546814 |
| keywords[7].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2207.14130 |
| 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/2207.14130 |
| 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/2207.14130 |
| locations[1].id | doi:10.48550/arxiv.2207.14130 |
| 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.2207.14130 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5079408504 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Divyansh Jhunjhunwala |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jhunjhunwala, Divyansh |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5028196076 |
| authorships[1].author.orcid | https://orcid.org/0009-0007-8027-7913 |
| authorships[1].author.display_name | Pranay Sharma |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sharma, Pranay |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5068373888 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Aushim Nagarkatti |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Nagarkatti, Aushim |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5067441201 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6372-9697 |
| authorships[3].author.display_name | Gauri Joshi |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Joshi, Gauri |
| authorships[3].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/2207.14130 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10764 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991000294685364 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Privacy-Preserving Technologies in Data |
| related_works | https://openalex.org/W4298130764, https://openalex.org/W2804364458, https://openalex.org/W2132641928, https://openalex.org/W4310225030, https://openalex.org/W2090259340, https://openalex.org/W2393816671, https://openalex.org/W2158836806, https://openalex.org/W2083665254, https://openalex.org/W1926736923, https://openalex.org/W2942177010 |
| cited_by_count | 7 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 1 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2207.14130 |
| 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/2207.14130 |
| 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/2207.14130 |
| primary_location.id | pmh:oai:arXiv.org:2207.14130 |
| 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/2207.14130 |
| 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/2207.14130 |
| publication_date | 2022-07-28 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 38, 71, 128 |
| abstract_inverted_index.1) | 13 |
| abstract_inverted_index.2) | 27 |
| abstract_inverted_index.To | 65, 88 |
| abstract_inverted_index.We | 50 |
| abstract_inverted_index.as | 107 |
| abstract_inverted_index.at | 24, 77, 123, 148 |
| abstract_inverted_index.by | 18, 33 |
| abstract_inverted_index.do | 89, 143 |
| abstract_inverted_index.in | 46, 62, 95, 114 |
| abstract_inverted_index.of | 10, 41, 152 |
| abstract_inverted_index.or | 150 |
| abstract_inverted_index.to | 84, 118, 171 |
| abstract_inverted_index.we | 68, 126, 159 |
| abstract_inverted_index.and | 26, 104, 141, 166 |
| abstract_inverted_index.due | 83 |
| abstract_inverted_index.for | 101, 110 |
| abstract_inverted_index.has | 58 |
| abstract_inverted_index.not | 144 |
| abstract_inverted_index.so, | 90 |
| abstract_inverted_index.the | 34, 42, 56, 63, 78, 91, 97, 111, 120, 124 |
| abstract_inverted_index.two | 7 |
| abstract_inverted_index.(FL) | 3 |
| abstract_inverted_index.both | 139 |
| abstract_inverted_index.each | 102 |
| abstract_inverted_index.edge | 43 |
| abstract_inverted_index.fact | 35 |
| abstract_inverted_index.find | 51 |
| abstract_inverted_index.from | 6 |
| abstract_inverted_index.less | 175 |
| abstract_inverted_index.most | 98 |
| abstract_inverted_index.much | 174 |
| abstract_inverted_index.only | 37, 55 |
| abstract_inverted_index.show | 160 |
| abstract_inverted_index.that | 36, 52, 80, 161 |
| abstract_inverted_index.uses | 105 |
| abstract_inverted_index.with | 173 |
| abstract_inverted_index.among | 53 |
| abstract_inverted_index.drift | 15 |
| abstract_inverted_index.error | 16, 31, 82 |
| abstract_inverted_index.every | 47, 115 |
| abstract_inverted_index.local | 21 |
| abstract_inverted_index.novel | 72, 129 |
| abstract_inverted_index.small | 39 |
| abstract_inverted_index.steps | 23 |
| abstract_inverted_index.these | 106 |
| abstract_inverted_index.this, | 67 |
| abstract_inverted_index.Unlike | 135 |
| abstract_inverted_index.caused | 17, 32 |
| abstract_inverted_index.client | 14, 29, 86, 103 |
| abstract_inverted_index.error: | 12 |
| abstract_inverted_index.former | 57 |
| abstract_inverted_index.memory | 96, 121, 176 |
| abstract_inverted_index.recent | 99 |
| abstract_inverted_index.remedy | 66 |
| abstract_inverted_index.round. | 49, 116 |
| abstract_inverted_index.server | 79, 92 |
| abstract_inverted_index.simply | 93 |
| abstract_inverted_index.subset | 40 |
| abstract_inverted_index.suffer | 5 |
| abstract_inverted_index.these, | 54 |
| abstract_inverted_index.update | 100 |
| abstract_inverted_index.FedVARP | 140, 162, 172 |
| abstract_inverted_index.Through | 156 |
| abstract_inverted_index.applied | 76 |
| abstract_inverted_index.clients | 44, 113, 149 |
| abstract_inverted_index.partial | 28, 85 |
| abstract_inverted_index.propose | 69, 127 |
| abstract_inverted_index.require | 145 |
| abstract_inverted_index.server, | 125 |
| abstract_inverted_index.sources | 9 |
| abstract_inverted_index.systems | 4 |
| abstract_inverted_index.updates | 109 |
| abstract_inverted_index.FedVARP, | 70 |
| abstract_inverted_index.Further, | 117 |
| abstract_inverted_index.achieves | 168 |
| abstract_inverted_index.clients, | 25 |
| abstract_inverted_index.learning | 2 |
| abstract_inverted_index.methods, | 138, 165 |
| abstract_inverted_index.multiple | 20 |
| abstract_inverted_index.proposed | 137 |
| abstract_inverted_index.received | 59 |
| abstract_inverted_index.training | 48 |
| abstract_inverted_index.variance | 73, 131 |
| abstract_inverted_index.algorithm | 75, 133 |
| abstract_inverted_index.alleviate | 119 |
| abstract_inverted_index.attention | 61 |
| abstract_inverted_index.extensive | 157 |
| abstract_inverted_index.federated | 1 |
| abstract_inverted_index.maintains | 94 |
| abstract_inverted_index.reduction | 74, 132 |
| abstract_inverted_index.surrogate | 108 |
| abstract_inverted_index.additional | 146, 153 |
| abstract_inverted_index.comparable | 170 |
| abstract_inverted_index.eliminates | 81 |
| abstract_inverted_index.performing | 19 |
| abstract_inverted_index.previously | 136 |
| abstract_inverted_index.computation | 147 |
| abstract_inverted_index.convergence | 11 |
| abstract_inverted_index.literature. | 64 |
| abstract_inverted_index.outperforms | 163 |
| abstract_inverted_index.parameters. | 155 |
| abstract_inverted_index.participate | 45 |
| abstract_inverted_index.performance | 169 |
| abstract_inverted_index.requirement | 122 |
| abstract_inverted_index.significant | 8, 60 |
| abstract_inverted_index.experiments, | 158 |
| abstract_inverted_index.optimization | 22, 154 |
| abstract_inverted_index.communication | 151 |
| abstract_inverted_index.participation | 30 |
| abstract_inverted_index.requirements. | 177 |
| abstract_inverted_index.ClusterFedVARP | 142, 167 |
| abstract_inverted_index.participation. | 87 |
| abstract_inverted_index.ClusterFedVARP. | 134 |
| abstract_inverted_index.clustering-based | 130 |
| abstract_inverted_index.state-of-the-art | 164 |
| abstract_inverted_index.non-participating | 112 |
| abstract_inverted_index.Data-heterogeneous | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |