STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation Article Swipe
Zhenzhen Guan
,
Guojun Zhu
,
Zhou Yucan
,
Wu Liu
,
Weiping Wang
,
Jiebo Luo
,
Xiaoyan Gu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2506.01327
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2506.01327
Federated Class-Incremental Learning (FCIL) enables Class-Incremental Learning (CIL) from distributed data. Existing FCIL methods typically integrate old knowledge preservation into local client training. However, these methods cannot avoid spatial-temporal client drift caused by data heterogeneity and often incur significant computational and communication overhead, limiting practical deployment. To address these challenges simultaneously, we propose a novel approach, Spatial-Temporal Statistics Aggregation (STSA), which provides a unified framework to aggregate feature statistics both spatially (across clients) and temporally (across stages). The aggregated feature statistics are unaffected by data heterogeneity and can be used to update the classifier in closed form at each stage. Additionally, we introduce STSA-E, a communication-efficient variant with theoretical guarantees, achieving similar performance to STSA-E with much lower communication overhead. Extensive experiments on three widely used FCIL datasets, with varying degrees of data heterogeneity, show that our method outperforms state-of-the-art FCIL methods in terms of performance, flexibility, and both communication and computation efficiency.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2506.01327
- https://arxiv.org/pdf/2506.01327
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414896274
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414896274Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2506.01327Digital Object Identifier
- Title
-
STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics AggregationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-02Full publication date if available
- Authors
-
Zhenzhen Guan, Guojun Zhu, Zhou Yucan, Wu Liu, Weiping Wang, Jiebo Luo, Xiaoyan GuList of authors in order
- Landing page
-
https://arxiv.org/abs/2506.01327Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2506.01327Direct 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/2506.01327Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414896274 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2506.01327 |
| ids.doi | https://doi.org/10.48550/arxiv.2506.01327 |
| ids.openalex | https://openalex.org/W4414896274 |
| fwci | |
| type | preprint |
| title | STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11980 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.9136000275611877 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3313 |
| topics[0].subfield.display_name | Transportation |
| topics[0].display_name | Human Mobility and Location-Based Analysis |
| topics[1].id | https://openalex.org/T10538 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9071000218391418 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1710 |
| topics[1].subfield.display_name | Information Systems |
| topics[1].display_name | Data Mining Algorithms and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2506.01327 |
| 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 | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2506.01327 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2506.01327 |
| locations[1].id | doi:10.48550/arxiv.2506.01327 |
| 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.2506.01327 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5051100169 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1042-7222 |
| authorships[0].author.display_name | Zhenzhen Guan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Guan, Zenghao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5052615408 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4277-4560 |
| authorships[1].author.display_name | Guojun Zhu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhu, Guojun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100985690 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Zhou Yucan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhou, Yucan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100743423 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-3058-2067 |
| authorships[3].author.display_name | Wu Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Liu, Wu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5115591448 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Weiping Wang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wang, Weiping |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5055469774 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4516-9729 |
| authorships[5].author.display_name | Jiebo Luo |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Luo, Jiebo |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5024344221 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0673-0058 |
| authorships[6].author.display_name | Xiaoyan Gu |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Gu, Xiaoyan |
| authorships[6].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2506.01327 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11980 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.9136000275611877 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3313 |
| primary_topic.subfield.display_name | Transportation |
| primary_topic.display_name | Human Mobility and Location-Based Analysis |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2506.01327 |
| 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 | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2506.01327 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| 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/2506.01327 |
| primary_location.id | pmh:oai:arXiv.org:2506.01327 |
| 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 | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2506.01327 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2506.01327 |
| publication_date | 2025-06-02 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 53, 62, 104 |
| abstract_inverted_index.To | 46 |
| abstract_inverted_index.at | 97 |
| abstract_inverted_index.be | 88 |
| abstract_inverted_index.by | 32, 83 |
| abstract_inverted_index.in | 94, 142 |
| abstract_inverted_index.of | 131, 144 |
| abstract_inverted_index.on | 122 |
| abstract_inverted_index.to | 65, 90, 113 |
| abstract_inverted_index.we | 51, 101 |
| abstract_inverted_index.The | 77 |
| abstract_inverted_index.and | 35, 40, 73, 86, 147, 150 |
| abstract_inverted_index.are | 81 |
| abstract_inverted_index.can | 87 |
| abstract_inverted_index.old | 16 |
| abstract_inverted_index.our | 136 |
| abstract_inverted_index.the | 92 |
| abstract_inverted_index.FCIL | 12, 126, 140 |
| abstract_inverted_index.both | 69, 148 |
| abstract_inverted_index.data | 33, 84, 132 |
| abstract_inverted_index.each | 98 |
| abstract_inverted_index.form | 96 |
| abstract_inverted_index.from | 8 |
| abstract_inverted_index.into | 19 |
| abstract_inverted_index.much | 116 |
| abstract_inverted_index.show | 134 |
| abstract_inverted_index.that | 135 |
| abstract_inverted_index.used | 89, 125 |
| abstract_inverted_index.with | 107, 115, 128 |
| abstract_inverted_index.(CIL) | 7 |
| abstract_inverted_index.avoid | 27 |
| abstract_inverted_index.data. | 10 |
| abstract_inverted_index.drift | 30 |
| abstract_inverted_index.incur | 37 |
| abstract_inverted_index.local | 20 |
| abstract_inverted_index.lower | 117 |
| abstract_inverted_index.novel | 54 |
| abstract_inverted_index.often | 36 |
| abstract_inverted_index.terms | 143 |
| abstract_inverted_index.these | 24, 48 |
| abstract_inverted_index.three | 123 |
| abstract_inverted_index.which | 60 |
| abstract_inverted_index.(FCIL) | 3 |
| abstract_inverted_index.STSA-E | 114 |
| abstract_inverted_index.cannot | 26 |
| abstract_inverted_index.caused | 31 |
| abstract_inverted_index.client | 21, 29 |
| abstract_inverted_index.closed | 95 |
| abstract_inverted_index.method | 137 |
| abstract_inverted_index.stage. | 99 |
| abstract_inverted_index.update | 91 |
| abstract_inverted_index.widely | 124 |
| abstract_inverted_index.(STSA), | 59 |
| abstract_inverted_index.(across | 71, 75 |
| abstract_inverted_index.STSA-E, | 103 |
| abstract_inverted_index.address | 47 |
| abstract_inverted_index.degrees | 130 |
| abstract_inverted_index.enables | 4 |
| abstract_inverted_index.feature | 67, 79 |
| abstract_inverted_index.methods | 13, 25, 141 |
| abstract_inverted_index.propose | 52 |
| abstract_inverted_index.similar | 111 |
| abstract_inverted_index.unified | 63 |
| abstract_inverted_index.variant | 106 |
| abstract_inverted_index.varying | 129 |
| abstract_inverted_index.Existing | 11 |
| abstract_inverted_index.However, | 23 |
| abstract_inverted_index.Learning | 2, 6 |
| abstract_inverted_index.clients) | 72 |
| abstract_inverted_index.limiting | 43 |
| abstract_inverted_index.provides | 61 |
| abstract_inverted_index.stages). | 76 |
| abstract_inverted_index.Extensive | 120 |
| abstract_inverted_index.Federated | 0 |
| abstract_inverted_index.achieving | 110 |
| abstract_inverted_index.aggregate | 66 |
| abstract_inverted_index.approach, | 55 |
| abstract_inverted_index.datasets, | 127 |
| abstract_inverted_index.framework | 64 |
| abstract_inverted_index.integrate | 15 |
| abstract_inverted_index.introduce | 102 |
| abstract_inverted_index.knowledge | 17 |
| abstract_inverted_index.overhead, | 42 |
| abstract_inverted_index.overhead. | 119 |
| abstract_inverted_index.practical | 44 |
| abstract_inverted_index.spatially | 70 |
| abstract_inverted_index.training. | 22 |
| abstract_inverted_index.typically | 14 |
| abstract_inverted_index.Statistics | 57 |
| abstract_inverted_index.aggregated | 78 |
| abstract_inverted_index.challenges | 49 |
| abstract_inverted_index.classifier | 93 |
| abstract_inverted_index.statistics | 68, 80 |
| abstract_inverted_index.temporally | 74 |
| abstract_inverted_index.unaffected | 82 |
| abstract_inverted_index.Aggregation | 58 |
| abstract_inverted_index.computation | 151 |
| abstract_inverted_index.deployment. | 45 |
| abstract_inverted_index.distributed | 9 |
| abstract_inverted_index.efficiency. | 152 |
| abstract_inverted_index.experiments | 121 |
| abstract_inverted_index.guarantees, | 109 |
| abstract_inverted_index.outperforms | 138 |
| abstract_inverted_index.performance | 112 |
| abstract_inverted_index.significant | 38 |
| abstract_inverted_index.theoretical | 108 |
| abstract_inverted_index.flexibility, | 146 |
| abstract_inverted_index.performance, | 145 |
| abstract_inverted_index.preservation | 18 |
| abstract_inverted_index.Additionally, | 100 |
| abstract_inverted_index.communication | 41, 118, 149 |
| abstract_inverted_index.computational | 39 |
| abstract_inverted_index.heterogeneity | 34, 85 |
| abstract_inverted_index.heterogeneity, | 133 |
| abstract_inverted_index.simultaneously, | 50 |
| abstract_inverted_index.Spatial-Temporal | 56 |
| abstract_inverted_index.spatial-temporal | 28 |
| abstract_inverted_index.state-of-the-art | 139 |
| abstract_inverted_index.Class-Incremental | 1, 5 |
| abstract_inverted_index.communication-efficient | 105 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |