On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data Article Swipe
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2206.04723
Existing theory predicts that data heterogeneity will degrade the performance of the Federated Averaging (FedAvg) algorithm in federated learning. However, in practice, the simple FedAvg algorithm converges very well. This paper explains the seemingly unreasonable effectiveness of FedAvg that contradicts the previous theoretical predictions. We find that the key assumption of bounded gradient dissimilarity in previous theoretical analyses is too pessimistic to characterize data heterogeneity in practical applications. For a simple quadratic problem, we demonstrate there exist regimes where large gradient dissimilarity does not have any negative impact on the convergence of FedAvg. Motivated by this observation, we propose a new quantity, average drift at optimum, to measure the effects of data heterogeneity, and explicitly use it to present a new theoretical analysis of FedAvg. We show that the average drift at optimum is nearly zero across many real-world federated training tasks, whereas the gradient dissimilarity can be large. And our new analysis suggests FedAvg can have identical convergence rates in homogeneous and heterogeneous data settings, and hence, leads to better understanding of its empirical success.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2206.04723
- https://arxiv.org/pdf/2206.04723
- OA Status
- green
- Cited By
- 19
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4282813193
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4282813193Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2206.04723Digital Object Identifier
- Title
-
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous DataWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-06-09Full publication date if available
- Authors
-
Jianyu Wang, Rudrajit Das, Gauri Joshi, Satyen Kale, Zheng Xu, Tong ZhangList of authors in order
- Landing page
-
https://arxiv.org/abs/2206.04723Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2206.04723Direct 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/2206.04723Direct OA link when available
- Concepts
-
Simple (philosophy), Computer science, Convergence (economics), Bounded function, Measure (data warehouse), Homogeneous, Pessimism, Quadratic equation, Rate of convergence, Concept drift, Key (lock), Mathematical optimization, Data mining, Mathematics, Economics, Data stream mining, Computer security, Combinatorics, Philosophy, Geometry, Economic growth, Epistemology, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
19Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 6, 2023: 12Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4282813193 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2206.04723 |
| ids.doi | https://doi.org/10.48550/arxiv.2206.04723 |
| ids.openalex | https://openalex.org/W4282813193 |
| fwci | |
| type | preprint |
| title | On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data |
| 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 |
| topics[1].id | https://openalex.org/T11344 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.995199978351593 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2215 |
| topics[1].subfield.display_name | Building and Construction |
| topics[1].display_name | Traffic Prediction and Management Techniques |
| topics[2].id | https://openalex.org/T11612 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9825999736785889 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Stochastic Gradient Optimization Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780586882 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6888573169708252 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7520643 |
| concepts[0].display_name | Simple (philosophy) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6708443760871887 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2777303404 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6454726457595825 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q759757 |
| concepts[2].display_name | Convergence (economics) |
| concepts[3].id | https://openalex.org/C34388435 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6022014021873474 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2267362 |
| concepts[3].display_name | Bounded function |
| concepts[4].id | https://openalex.org/C2780009758 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5570225715637207 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q6804172 |
| concepts[4].display_name | Measure (data warehouse) |
| concepts[5].id | https://openalex.org/C66882249 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5444768667221069 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q169336 |
| concepts[5].display_name | Homogeneous |
| concepts[6].id | https://openalex.org/C9992130 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5259276032447815 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q484954 |
| concepts[6].display_name | Pessimism |
| concepts[7].id | https://openalex.org/C129844170 |
| concepts[7].level | 2 |
| concepts[7].score | 0.48079290986061096 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q41299 |
| concepts[7].display_name | Quadratic equation |
| concepts[8].id | https://openalex.org/C57869625 |
| concepts[8].level | 3 |
| concepts[8].score | 0.4497992694377899 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1783502 |
| concepts[8].display_name | Rate of convergence |
| concepts[9].id | https://openalex.org/C60777511 |
| concepts[9].level | 3 |
| concepts[9].score | 0.42315420508384705 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3045002 |
| concepts[9].display_name | Concept drift |
| concepts[10].id | https://openalex.org/C26517878 |
| concepts[10].level | 2 |
| concepts[10].score | 0.38268449902534485 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q228039 |
| concepts[10].display_name | Key (lock) |
| concepts[11].id | https://openalex.org/C126255220 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3300474286079407 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[11].display_name | Mathematical optimization |
| concepts[12].id | https://openalex.org/C124101348 |
| concepts[12].level | 1 |
| concepts[12].score | 0.32390618324279785 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[12].display_name | Data mining |
| concepts[13].id | https://openalex.org/C33923547 |
| concepts[13].level | 0 |
| concepts[13].score | 0.25244343280792236 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[13].display_name | Mathematics |
| concepts[14].id | https://openalex.org/C162324750 |
| concepts[14].level | 0 |
| concepts[14].score | 0.07063648104667664 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[14].display_name | Economics |
| concepts[15].id | https://openalex.org/C89198739 |
| concepts[15].level | 2 |
| concepts[15].score | 0.06631284952163696 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q3079880 |
| concepts[15].display_name | Data stream mining |
| concepts[16].id | https://openalex.org/C38652104 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[16].display_name | Computer security |
| concepts[17].id | https://openalex.org/C114614502 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q76592 |
| concepts[17].display_name | Combinatorics |
| concepts[18].id | https://openalex.org/C138885662 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[18].display_name | Philosophy |
| concepts[19].id | https://openalex.org/C2524010 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[19].display_name | Geometry |
| concepts[20].id | https://openalex.org/C50522688 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q189833 |
| concepts[20].display_name | Economic growth |
| concepts[21].id | https://openalex.org/C111472728 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[21].display_name | Epistemology |
| concepts[22].id | https://openalex.org/C134306372 |
| concepts[22].level | 1 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[22].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/simple |
| keywords[0].score | 0.6888573169708252 |
| keywords[0].display_name | Simple (philosophy) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6708443760871887 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/convergence |
| keywords[2].score | 0.6454726457595825 |
| keywords[2].display_name | Convergence (economics) |
| keywords[3].id | https://openalex.org/keywords/bounded-function |
| keywords[3].score | 0.6022014021873474 |
| keywords[3].display_name | Bounded function |
| keywords[4].id | https://openalex.org/keywords/measure |
| keywords[4].score | 0.5570225715637207 |
| keywords[4].display_name | Measure (data warehouse) |
| keywords[5].id | https://openalex.org/keywords/homogeneous |
| keywords[5].score | 0.5444768667221069 |
| keywords[5].display_name | Homogeneous |
| keywords[6].id | https://openalex.org/keywords/pessimism |
| keywords[6].score | 0.5259276032447815 |
| keywords[6].display_name | Pessimism |
| keywords[7].id | https://openalex.org/keywords/quadratic-equation |
| keywords[7].score | 0.48079290986061096 |
| keywords[7].display_name | Quadratic equation |
| keywords[8].id | https://openalex.org/keywords/rate-of-convergence |
| keywords[8].score | 0.4497992694377899 |
| keywords[8].display_name | Rate of convergence |
| keywords[9].id | https://openalex.org/keywords/concept-drift |
| keywords[9].score | 0.42315420508384705 |
| keywords[9].display_name | Concept drift |
| keywords[10].id | https://openalex.org/keywords/key |
| keywords[10].score | 0.38268449902534485 |
| keywords[10].display_name | Key (lock) |
| keywords[11].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[11].score | 0.3300474286079407 |
| keywords[11].display_name | Mathematical optimization |
| keywords[12].id | https://openalex.org/keywords/data-mining |
| keywords[12].score | 0.32390618324279785 |
| keywords[12].display_name | Data mining |
| keywords[13].id | https://openalex.org/keywords/mathematics |
| keywords[13].score | 0.25244343280792236 |
| keywords[13].display_name | Mathematics |
| keywords[14].id | https://openalex.org/keywords/economics |
| keywords[14].score | 0.07063648104667664 |
| keywords[14].display_name | Economics |
| keywords[15].id | https://openalex.org/keywords/data-stream-mining |
| keywords[15].score | 0.06631284952163696 |
| keywords[15].display_name | Data stream mining |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2206.04723 |
| 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/2206.04723 |
| 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/2206.04723 |
| locations[1].id | doi:10.48550/arxiv.2206.04723 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2206.04723 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100398977 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-7075-9333 |
| authorships[0].author.display_name | Jianyu Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Jianyu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5037384125 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Rudrajit Das |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Das, Rudrajit |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5067441201 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6372-9697 |
| authorships[2].author.display_name | Gauri Joshi |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Joshi, Gauri |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5114021051 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Satyen Kale |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Kale, Satyen |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100413782 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0648-0327 |
| authorships[4].author.display_name | Zheng Xu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xu, Zheng |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100378750 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-5818-4285 |
| authorships[5].author.display_name | Tong Zhang |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Zhang, Tong |
| authorships[5].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/2206.04723 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data |
| 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/W4380987628, https://openalex.org/W2418537576, https://openalex.org/W2557514562, https://openalex.org/W214945085, https://openalex.org/W1987935396, https://openalex.org/W3126025002, https://openalex.org/W2990081132, https://openalex.org/W2354456418, https://openalex.org/W2080168062, https://openalex.org/W4287117439 |
| cited_by_count | 19 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 6 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 12 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2206.04723 |
| 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/2206.04723 |
| 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/2206.04723 |
| primary_location.id | pmh:oai:arXiv.org:2206.04723 |
| 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/2206.04723 |
| 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/2206.04723 |
| publication_date | 2022-06-09 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 69, 99, 119 |
| abstract_inverted_index.We | 44, 125 |
| abstract_inverted_index.at | 104, 131 |
| abstract_inverted_index.be | 147 |
| abstract_inverted_index.by | 94 |
| abstract_inverted_index.in | 16, 20, 54, 65, 160 |
| abstract_inverted_index.is | 58, 133 |
| abstract_inverted_index.it | 116 |
| abstract_inverted_index.of | 10, 36, 50, 91, 110, 123, 172 |
| abstract_inverted_index.on | 88 |
| abstract_inverted_index.to | 61, 106, 117, 169 |
| abstract_inverted_index.we | 73, 97 |
| abstract_inverted_index.And | 149 |
| abstract_inverted_index.For | 68 |
| abstract_inverted_index.and | 113, 162, 166 |
| abstract_inverted_index.any | 85 |
| abstract_inverted_index.can | 146, 155 |
| abstract_inverted_index.its | 173 |
| abstract_inverted_index.key | 48 |
| abstract_inverted_index.new | 100, 120, 151 |
| abstract_inverted_index.not | 83 |
| abstract_inverted_index.our | 150 |
| abstract_inverted_index.the | 8, 11, 22, 32, 40, 47, 89, 108, 128, 143 |
| abstract_inverted_index.too | 59 |
| abstract_inverted_index.use | 115 |
| abstract_inverted_index.This | 29 |
| abstract_inverted_index.data | 4, 63, 111, 164 |
| abstract_inverted_index.does | 82 |
| abstract_inverted_index.find | 45 |
| abstract_inverted_index.have | 84, 156 |
| abstract_inverted_index.many | 137 |
| abstract_inverted_index.show | 126 |
| abstract_inverted_index.that | 3, 38, 46, 127 |
| abstract_inverted_index.this | 95 |
| abstract_inverted_index.very | 27 |
| abstract_inverted_index.will | 6 |
| abstract_inverted_index.zero | 135 |
| abstract_inverted_index.drift | 103, 130 |
| abstract_inverted_index.exist | 76 |
| abstract_inverted_index.large | 79 |
| abstract_inverted_index.leads | 168 |
| abstract_inverted_index.paper | 30 |
| abstract_inverted_index.rates | 159 |
| abstract_inverted_index.there | 75 |
| abstract_inverted_index.well. | 28 |
| abstract_inverted_index.where | 78 |
| abstract_inverted_index.FedAvg | 24, 37, 154 |
| abstract_inverted_index.across | 136 |
| abstract_inverted_index.better | 170 |
| abstract_inverted_index.hence, | 167 |
| abstract_inverted_index.impact | 87 |
| abstract_inverted_index.large. | 148 |
| abstract_inverted_index.nearly | 134 |
| abstract_inverted_index.simple | 23, 70 |
| abstract_inverted_index.tasks, | 141 |
| abstract_inverted_index.theory | 1 |
| abstract_inverted_index.FedAvg. | 92, 124 |
| abstract_inverted_index.average | 102, 129 |
| abstract_inverted_index.bounded | 51 |
| abstract_inverted_index.degrade | 7 |
| abstract_inverted_index.effects | 109 |
| abstract_inverted_index.measure | 107 |
| abstract_inverted_index.optimum | 132 |
| abstract_inverted_index.present | 118 |
| abstract_inverted_index.propose | 98 |
| abstract_inverted_index.regimes | 77 |
| abstract_inverted_index.whereas | 142 |
| abstract_inverted_index.(FedAvg) | 14 |
| abstract_inverted_index.Existing | 0 |
| abstract_inverted_index.However, | 19 |
| abstract_inverted_index.analyses | 57 |
| abstract_inverted_index.analysis | 122, 152 |
| abstract_inverted_index.explains | 31 |
| abstract_inverted_index.gradient | 52, 80, 144 |
| abstract_inverted_index.negative | 86 |
| abstract_inverted_index.optimum, | 105 |
| abstract_inverted_index.predicts | 2 |
| abstract_inverted_index.previous | 41, 55 |
| abstract_inverted_index.problem, | 72 |
| abstract_inverted_index.success. | 175 |
| abstract_inverted_index.suggests | 153 |
| abstract_inverted_index.training | 140 |
| abstract_inverted_index.Averaging | 13 |
| abstract_inverted_index.Federated | 12 |
| abstract_inverted_index.Motivated | 93 |
| abstract_inverted_index.algorithm | 15, 25 |
| abstract_inverted_index.converges | 26 |
| abstract_inverted_index.empirical | 174 |
| abstract_inverted_index.federated | 17, 139 |
| abstract_inverted_index.identical | 157 |
| abstract_inverted_index.learning. | 18 |
| abstract_inverted_index.practical | 66 |
| abstract_inverted_index.practice, | 21 |
| abstract_inverted_index.quadratic | 71 |
| abstract_inverted_index.quantity, | 101 |
| abstract_inverted_index.seemingly | 33 |
| abstract_inverted_index.settings, | 165 |
| abstract_inverted_index.assumption | 49 |
| abstract_inverted_index.explicitly | 114 |
| abstract_inverted_index.real-world | 138 |
| abstract_inverted_index.contradicts | 39 |
| abstract_inverted_index.convergence | 90, 158 |
| abstract_inverted_index.demonstrate | 74 |
| abstract_inverted_index.homogeneous | 161 |
| abstract_inverted_index.performance | 9 |
| abstract_inverted_index.pessimistic | 60 |
| abstract_inverted_index.theoretical | 42, 56, 121 |
| abstract_inverted_index.characterize | 62 |
| abstract_inverted_index.observation, | 96 |
| abstract_inverted_index.predictions. | 43 |
| abstract_inverted_index.unreasonable | 34 |
| abstract_inverted_index.applications. | 67 |
| abstract_inverted_index.dissimilarity | 53, 81, 145 |
| abstract_inverted_index.effectiveness | 35 |
| abstract_inverted_index.heterogeneity | 5, 64 |
| abstract_inverted_index.heterogeneous | 163 |
| abstract_inverted_index.understanding | 171 |
| abstract_inverted_index.heterogeneity, | 112 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |