DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation Article Swipe
Maolin Wang
,
Ting Wei
,
Sheng Zhang
,
Ruocheng Guo
,
Wanyu Wang
,
Shanshan Ye
,
Lixin Zou
,
Xuetao Wei
,
Xiangyu Zhao
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.04671
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.04671
Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, each deployment context requires costly separate searches, and performance consistency across diverse platforms remains challenging. We propose DANCE (Dynamic Architectures with Neural Continuous Evolution), which reformulates architecture search as a continuous evolution problem through learning distributions over architectural components. DANCE introduces three key innovations: a continuous architecture distribution enabling smooth adaptation, a unified architecture space with learned selection gates for efficient sampling, and a multi-stage training strategy for effective deployment optimization. Extensive experiments across five datasets demonstrate DANCE's effectiveness. Our method consistently outperforms state-of-the-art NAS approaches in terms of accuracy while significantly reducing search costs. Under varying computational constraints, DANCE maintains robust performance while smoothly adapting architectures to different hardware requirements. The code and appendix can be found at https://github.com/Applied-Machine-Learning-Lab/DANCE.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.04671
- https://arxiv.org/pdf/2507.04671
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415163523
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415163523Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.04671Digital Object Identifier
- Title
-
DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous AdaptationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-07Full publication date if available
- Authors
-
Maolin Wang, Ting Wei, Sheng Zhang, Ruocheng Guo, Wanyu Wang, Shanshan Ye, Lixin Zou, Xuetao Wei, Xiangyu ZhaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.04671Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.04671Direct 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/2507.04671Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415163523 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.04671 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.04671 |
| ids.openalex | https://openalex.org/W4415163523 |
| fwci | |
| type | preprint |
| title | DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.983299970626831 |
| 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 | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9708999991416931 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9613999724388123 |
| 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 | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.04671 |
| 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/2507.04671 |
| 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/2507.04671 |
| locations[1].id | doi:10.48550/arxiv.2507.04671 |
| 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.2507.04671 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5021037797 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-0073-0172 |
| authorships[0].author.display_name | Maolin Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Maolin |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5085753115 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6058-6806 |
| authorships[1].author.display_name | Ting Wei |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wei, Tianshuo |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5009286900 |
| authorships[2].author.orcid | https://orcid.org/0009-0006-1758-6708 |
| authorships[2].author.display_name | Sheng Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Sheng |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5054719216 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8522-6142 |
| authorships[3].author.display_name | Ruocheng Guo |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Guo, Ruocheng |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5059573675 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-5976-0707 |
| authorships[4].author.display_name | Wanyu Wang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wang, Wanyu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5056384174 |
| authorships[5].author.orcid | https://orcid.org/0009-0003-6961-7455 |
| authorships[5].author.display_name | Shanshan Ye |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Ye, Shanshan |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5089307887 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-6755-871X |
| authorships[6].author.display_name | Lixin Zou |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Zou, Lixin |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5003379167 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-4450-2251 |
| authorships[7].author.display_name | Xuetao Wei |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Wei, Xuetao |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5100645854 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-2926-4416 |
| authorships[8].author.display_name | Xiangyu Zhao |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Zhao, Xiangyu |
| authorships[8].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/2507.04671 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-14T00:00:00 |
| display_name | DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.983299970626831 |
| 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 | Neural Networks and Applications |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.04671 |
| 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/2507.04671 |
| 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/2507.04671 |
| primary_location.id | pmh:oai:arXiv.org:2507.04671 |
| 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/2507.04671 |
| 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/2507.04671 |
| publication_date | 2025-07-07 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 7, 59, 74, 81, 93 |
| abstract_inverted_index.We | 45 |
| abstract_inverted_index.as | 6, 58 |
| abstract_inverted_index.at | 148 |
| abstract_inverted_index.be | 146 |
| abstract_inverted_index.in | 22, 116 |
| abstract_inverted_index.of | 118 |
| abstract_inverted_index.to | 137 |
| abstract_inverted_index.NAS | 17, 114 |
| abstract_inverted_index.Our | 109 |
| abstract_inverted_index.The | 141 |
| abstract_inverted_index.and | 37, 92, 143 |
| abstract_inverted_index.can | 145 |
| abstract_inverted_index.for | 10, 89, 97 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.key | 72 |
| abstract_inverted_index.code | 142 |
| abstract_inverted_index.each | 30 |
| abstract_inverted_index.face | 19 |
| abstract_inverted_index.five | 104 |
| abstract_inverted_index.lack | 26 |
| abstract_inverted_index.over | 66 |
| abstract_inverted_index.with | 50, 85 |
| abstract_inverted_index.(NAS) | 3 |
| abstract_inverted_index.DANCE | 47, 69, 129 |
| abstract_inverted_index.Under | 125 |
| abstract_inverted_index.found | 147 |
| abstract_inverted_index.gates | 88 |
| abstract_inverted_index.space | 84 |
| abstract_inverted_index.terms | 117 |
| abstract_inverted_index.three | 71 |
| abstract_inverted_index.which | 54 |
| abstract_inverted_index.while | 120, 133 |
| abstract_inverted_index.Neural | 0, 51 |
| abstract_inverted_index.Search | 2 |
| abstract_inverted_index.across | 28, 40, 103 |
| abstract_inverted_index.costly | 34 |
| abstract_inverted_index.costs. | 124 |
| abstract_inverted_index.method | 110 |
| abstract_inverted_index.neural | 12 |
| abstract_inverted_index.robust | 131 |
| abstract_inverted_index.search | 57, 123 |
| abstract_inverted_index.smooth | 79 |
| abstract_inverted_index.DANCE's | 107 |
| abstract_inverted_index.context | 32 |
| abstract_inverted_index.design. | 14 |
| abstract_inverted_index.diverse | 41 |
| abstract_inverted_index.emerged | 5 |
| abstract_inverted_index.learned | 86 |
| abstract_inverted_index.methods | 18 |
| abstract_inverted_index.network | 13 |
| abstract_inverted_index.problem | 62 |
| abstract_inverted_index.propose | 46 |
| abstract_inverted_index.remains | 43 |
| abstract_inverted_index.through | 63 |
| abstract_inverted_index.unified | 82 |
| abstract_inverted_index.varying | 126 |
| abstract_inverted_index.(Dynamic | 48 |
| abstract_inverted_index.However, | 15 |
| abstract_inverted_index.accuracy | 119 |
| abstract_inverted_index.adapting | 135 |
| abstract_inverted_index.appendix | 144 |
| abstract_inverted_index.approach | 9 |
| abstract_inverted_index.critical | 20 |
| abstract_inverted_index.datasets | 105 |
| abstract_inverted_index.enabling | 78 |
| abstract_inverted_index.existing | 16 |
| abstract_inverted_index.hardware | 139 |
| abstract_inverted_index.learning | 64 |
| abstract_inverted_index.powerful | 8 |
| abstract_inverted_index.reducing | 122 |
| abstract_inverted_index.requires | 33 |
| abstract_inverted_index.separate | 35 |
| abstract_inverted_index.smoothly | 134 |
| abstract_inverted_index.strategy | 96 |
| abstract_inverted_index.training | 95 |
| abstract_inverted_index.Extensive | 101 |
| abstract_inverted_index.different | 138 |
| abstract_inverted_index.effective | 98 |
| abstract_inverted_index.efficient | 90 |
| abstract_inverted_index.evolution | 61 |
| abstract_inverted_index.maintains | 130 |
| abstract_inverted_index.platforms | 42 |
| abstract_inverted_index.sampling, | 91 |
| abstract_inverted_index.searches, | 36 |
| abstract_inverted_index.selection | 87 |
| abstract_inverted_index.Continuous | 52 |
| abstract_inverted_index.approaches | 115 |
| abstract_inverted_index.automating | 11 |
| abstract_inverted_index.continuous | 60, 75 |
| abstract_inverted_index.deployment | 31, 99 |
| abstract_inverted_index.introduces | 70 |
| abstract_inverted_index.real-world | 23 |
| abstract_inverted_index.scenarios, | 29 |
| abstract_inverted_index.Evolution), | 53 |
| abstract_inverted_index.adaptation, | 80 |
| abstract_inverted_index.components. | 68 |
| abstract_inverted_index.consistency | 39 |
| abstract_inverted_index.demonstrate | 106 |
| abstract_inverted_index.experiments | 102 |
| abstract_inverted_index.limitations | 21 |
| abstract_inverted_index.multi-stage | 94 |
| abstract_inverted_index.outperforms | 112 |
| abstract_inverted_index.performance | 38, 132 |
| abstract_inverted_index.Architecture | 1 |
| abstract_inverted_index.adaptability | 27 |
| abstract_inverted_index.architecture | 56, 76, 83 |
| abstract_inverted_index.challenging. | 44 |
| abstract_inverted_index.consistently | 111 |
| abstract_inverted_index.constraints, | 128 |
| abstract_inverted_index.deployments: | 24 |
| abstract_inverted_index.distribution | 77 |
| abstract_inverted_index.innovations: | 73 |
| abstract_inverted_index.reformulates | 55 |
| abstract_inverted_index.Architectures | 49 |
| abstract_inverted_index.architectural | 67 |
| abstract_inverted_index.architectures | 25, 136 |
| abstract_inverted_index.computational | 127 |
| abstract_inverted_index.distributions | 65 |
| abstract_inverted_index.optimization. | 100 |
| abstract_inverted_index.requirements. | 140 |
| abstract_inverted_index.significantly | 121 |
| abstract_inverted_index.effectiveness. | 108 |
| abstract_inverted_index.state-of-the-art | 113 |
| abstract_inverted_index.https://github.com/Applied-Machine-Learning-Lab/DANCE. | 149 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile |