Towards Sparsified Federated Neuroimaging Models via Weight Pruning Article Swipe
Dimitris Stripelis
,
Umang Gupta
,
Nikhil J. Dhinagar
,
Greg Ver Steeg
,
Paul M. Thompson
,
José Luis Ambite
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.11669
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2208.11669
Federated training of large deep neural networks can often be restrictive due to the increasing costs of communicating the updates with increasing model sizes. Various model pruning techniques have been designed in centralized settings to reduce inference times. Combining centralized pruning techniques with federated training seems intuitive for reducing communication costs -- by pruning the model parameters right before the communication step. Moreover, such a progressive model pruning approach during training can also reduce training times/costs. To this end, we propose FedSparsify, which performs model pruning during federated training. In our experiments in centralized and federated settings on the brain age prediction task (estimating a person's age from their brain MRI), we demonstrate that models can be pruned up to 95% sparsity without affecting performance even in challenging federated learning environments with highly heterogeneous data distributions. One surprising benefit of model pruning is improved model privacy. We demonstrate that models with high sparsity are less susceptible to membership inference attacks, a type of privacy attack.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2208.11669
- https://arxiv.org/pdf/2208.11669
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4293138734
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4293138734Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2208.11669Digital Object Identifier
- Title
-
Towards Sparsified Federated Neuroimaging Models via Weight PruningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-08-24Full publication date if available
- Authors
-
Dimitris Stripelis, Umang Gupta, Nikhil J. Dhinagar, Greg Ver Steeg, Paul M. Thompson, José Luis AmbiteList of authors in order
- Landing page
-
https://arxiv.org/abs/2208.11669Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2208.11669Direct 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/2208.11669Direct OA link when available
- Concepts
-
Pruning, Computer science, Inference, Machine learning, Federated learning, Artificial intelligence, Deep neural networks, Task (project management), Artificial neural network, Deep learning, Training set, Economics, Agronomy, Biology, ManagementTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4293138734 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2208.11669 |
| ids.doi | https://doi.org/10.48550/arxiv.2208.11669 |
| ids.openalex | https://openalex.org/W4293138734 |
| fwci | |
| type | preprint |
| title | Towards Sparsified Federated Neuroimaging Models via Weight Pruning |
| 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 | 0.9988999962806702 |
| 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/T11612 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9900000095367432 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Stochastic Gradient Optimization Techniques |
| topics[2].id | https://openalex.org/T10241 |
| topics[2].field.id | https://openalex.org/fields/28 |
| topics[2].field.display_name | Neuroscience |
| topics[2].score | 0.9704999923706055 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2805 |
| topics[2].subfield.display_name | Cognitive Neuroscience |
| topics[2].display_name | Functional Brain Connectivity Studies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C108010975 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9021898508071899 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[0].display_name | Pruning |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8202351331710815 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7655940651893616 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6332055926322937 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C2992525071 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6257816553115845 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q50818671 |
| concepts[4].display_name | Federated learning |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5663089752197266 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C2984842247 |
| concepts[6].level | 3 |
| concepts[6].score | 0.4749208390712738 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[6].display_name | Deep neural networks |
| concepts[7].id | https://openalex.org/C2780451532 |
| concepts[7].level | 2 |
| concepts[7].score | 0.44820430874824524 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[7].display_name | Task (project management) |
| concepts[8].id | https://openalex.org/C50644808 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4414331316947937 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[8].display_name | Artificial neural network |
| concepts[9].id | https://openalex.org/C108583219 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4257684350013733 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[9].display_name | Deep learning |
| concepts[10].id | https://openalex.org/C51632099 |
| concepts[10].level | 2 |
| concepts[10].score | 0.413443386554718 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3985153 |
| concepts[10].display_name | Training set |
| concepts[11].id | https://openalex.org/C162324750 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[11].display_name | Economics |
| concepts[12].id | https://openalex.org/C6557445 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[12].display_name | Agronomy |
| concepts[13].id | https://openalex.org/C86803240 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[13].display_name | Biology |
| concepts[14].id | https://openalex.org/C187736073 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2920921 |
| concepts[14].display_name | Management |
| keywords[0].id | https://openalex.org/keywords/pruning |
| keywords[0].score | 0.9021898508071899 |
| keywords[0].display_name | Pruning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8202351331710815 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.7655940651893616 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.6332055926322937 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/federated-learning |
| keywords[4].score | 0.6257816553115845 |
| keywords[4].display_name | Federated learning |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5663089752197266 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[6].score | 0.4749208390712738 |
| keywords[6].display_name | Deep neural networks |
| keywords[7].id | https://openalex.org/keywords/task |
| keywords[7].score | 0.44820430874824524 |
| keywords[7].display_name | Task (project management) |
| keywords[8].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[8].score | 0.4414331316947937 |
| keywords[8].display_name | Artificial neural network |
| keywords[9].id | https://openalex.org/keywords/deep-learning |
| keywords[9].score | 0.4257684350013733 |
| keywords[9].display_name | Deep learning |
| keywords[10].id | https://openalex.org/keywords/training-set |
| keywords[10].score | 0.413443386554718 |
| keywords[10].display_name | Training set |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2208.11669 |
| 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/2208.11669 |
| 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/2208.11669 |
| locations[1].id | doi:10.48550/arxiv.2208.11669 |
| 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.2208.11669 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5015466855 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3343-8335 |
| authorships[0].author.display_name | Dimitris Stripelis |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Stripelis, Dimitris |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5081316458 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1263-8813 |
| authorships[1].author.display_name | Umang Gupta |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gupta, Umang |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5089189717 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-2424-4854 |
| authorships[2].author.display_name | Nikhil J. Dhinagar |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Dhinagar, Nikhil |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5075920466 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0793-141X |
| authorships[3].author.display_name | Greg Ver Steeg |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Steeg, Greg Ver |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100606557 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-4720-8867 |
| authorships[4].author.display_name | Paul M. Thompson |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Thompson, Paul |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5033175043 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-0087-080X |
| authorships[5].author.display_name | José Luis Ambite |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Ambite, José Luis |
| 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/2208.11669 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Towards Sparsified Federated Neuroimaging Models via Weight Pruning |
| 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 | 0.9988999962806702 |
| 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/W4298221930, https://openalex.org/W2777914285, https://openalex.org/W3013363440, https://openalex.org/W4287823391, https://openalex.org/W2373300491, https://openalex.org/W4280588203, https://openalex.org/W4287323461, https://openalex.org/W3042419602, https://openalex.org/W2966649771, https://openalex.org/W3000197790 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2208.11669 |
| 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/2208.11669 |
| 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/2208.11669 |
| primary_location.id | pmh:oai:arXiv.org:2208.11669 |
| 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/2208.11669 |
| 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/2208.11669 |
| publication_date | 2022-08-24 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 64, 104, 160 |
| abstract_inverted_index.-- | 51 |
| abstract_inverted_index.In | 89 |
| abstract_inverted_index.To | 76 |
| abstract_inverted_index.We | 146 |
| abstract_inverted_index.be | 9, 116 |
| abstract_inverted_index.by | 52 |
| abstract_inverted_index.in | 31, 92, 126 |
| abstract_inverted_index.is | 142 |
| abstract_inverted_index.of | 2, 16, 139, 162 |
| abstract_inverted_index.on | 97 |
| abstract_inverted_index.to | 12, 34, 119, 156 |
| abstract_inverted_index.up | 118 |
| abstract_inverted_index.we | 79, 111 |
| abstract_inverted_index.95% | 120 |
| abstract_inverted_index.One | 136 |
| abstract_inverted_index.age | 100, 106 |
| abstract_inverted_index.and | 94 |
| abstract_inverted_index.are | 153 |
| abstract_inverted_index.can | 7, 71, 115 |
| abstract_inverted_index.due | 11 |
| abstract_inverted_index.for | 47 |
| abstract_inverted_index.our | 90 |
| abstract_inverted_index.the | 13, 18, 54, 59, 98 |
| abstract_inverted_index.also | 72 |
| abstract_inverted_index.been | 29 |
| abstract_inverted_index.data | 134 |
| abstract_inverted_index.deep | 4 |
| abstract_inverted_index.end, | 78 |
| abstract_inverted_index.even | 125 |
| abstract_inverted_index.from | 107 |
| abstract_inverted_index.have | 28 |
| abstract_inverted_index.high | 151 |
| abstract_inverted_index.less | 154 |
| abstract_inverted_index.such | 63 |
| abstract_inverted_index.task | 102 |
| abstract_inverted_index.that | 113, 148 |
| abstract_inverted_index.this | 77 |
| abstract_inverted_index.type | 161 |
| abstract_inverted_index.with | 20, 42, 131, 150 |
| abstract_inverted_index.MRI), | 110 |
| abstract_inverted_index.brain | 99, 109 |
| abstract_inverted_index.costs | 15, 50 |
| abstract_inverted_index.large | 3 |
| abstract_inverted_index.model | 22, 25, 55, 66, 84, 140, 144 |
| abstract_inverted_index.often | 8 |
| abstract_inverted_index.right | 57 |
| abstract_inverted_index.seems | 45 |
| abstract_inverted_index.step. | 61 |
| abstract_inverted_index.their | 108 |
| abstract_inverted_index.which | 82 |
| abstract_inverted_index.before | 58 |
| abstract_inverted_index.during | 69, 86 |
| abstract_inverted_index.highly | 132 |
| abstract_inverted_index.models | 114, 149 |
| abstract_inverted_index.neural | 5 |
| abstract_inverted_index.pruned | 117 |
| abstract_inverted_index.reduce | 35, 73 |
| abstract_inverted_index.sizes. | 23 |
| abstract_inverted_index.times. | 37 |
| abstract_inverted_index.Various | 24 |
| abstract_inverted_index.attack. | 164 |
| abstract_inverted_index.benefit | 138 |
| abstract_inverted_index.privacy | 163 |
| abstract_inverted_index.propose | 80 |
| abstract_inverted_index.pruning | 26, 40, 53, 67, 85, 141 |
| abstract_inverted_index.updates | 19 |
| abstract_inverted_index.without | 122 |
| abstract_inverted_index.approach | 68 |
| abstract_inverted_index.attacks, | 159 |
| abstract_inverted_index.designed | 30 |
| abstract_inverted_index.improved | 143 |
| abstract_inverted_index.learning | 129 |
| abstract_inverted_index.networks | 6 |
| abstract_inverted_index.performs | 83 |
| abstract_inverted_index.person's | 105 |
| abstract_inverted_index.privacy. | 145 |
| abstract_inverted_index.reducing | 48 |
| abstract_inverted_index.settings | 33, 96 |
| abstract_inverted_index.sparsity | 121, 152 |
| abstract_inverted_index.training | 1, 44, 70, 74 |
| abstract_inverted_index.Combining | 38 |
| abstract_inverted_index.Federated | 0 |
| abstract_inverted_index.Moreover, | 62 |
| abstract_inverted_index.affecting | 123 |
| abstract_inverted_index.federated | 43, 87, 95, 128 |
| abstract_inverted_index.inference | 36, 158 |
| abstract_inverted_index.intuitive | 46 |
| abstract_inverted_index.training. | 88 |
| abstract_inverted_index.increasing | 14, 21 |
| abstract_inverted_index.membership | 157 |
| abstract_inverted_index.parameters | 56 |
| abstract_inverted_index.prediction | 101 |
| abstract_inverted_index.surprising | 137 |
| abstract_inverted_index.techniques | 27, 41 |
| abstract_inverted_index.(estimating | 103 |
| abstract_inverted_index.centralized | 32, 39, 93 |
| abstract_inverted_index.challenging | 127 |
| abstract_inverted_index.demonstrate | 112, 147 |
| abstract_inverted_index.experiments | 91 |
| abstract_inverted_index.performance | 124 |
| abstract_inverted_index.progressive | 65 |
| abstract_inverted_index.restrictive | 10 |
| abstract_inverted_index.susceptible | 155 |
| abstract_inverted_index.FedSparsify, | 81 |
| abstract_inverted_index.environments | 130 |
| abstract_inverted_index.times/costs. | 75 |
| abstract_inverted_index.communicating | 17 |
| abstract_inverted_index.communication | 49, 60 |
| abstract_inverted_index.heterogeneous | 133 |
| abstract_inverted_index.distributions. | 135 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |