Know2Vec: A Black-Box Proxy for Neural Network Retrieval Article Swipe
Z. J. Shang
,
Yanwei Liu
,
Jinxia Liu
,
Xiaoyan Gu
,
Ying Ding
,
Xiangyang Ji
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i19.34241
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1609/aaai.v39i19.34241
For general users, training a neural network from scratch is usually challenging and labor-intensive. Fortunately, neural network zoos enable them to find a well-performing model for directly use or fine-tuning it in their local environments. Although current model retrieval solutions attempt to convert neural network models into vectors to avoid complex multiple inference processes required for model selection, it is still difficult to choose a suitable model due to inaccurate vectorization and biased correlation alignment between the query dataset and models. From the perspective of knowledge consistency, i.e., whether the knowledge possessed by the model can meet the needs of query tasks, we propose a model retrieval scheme, named Know2Vec, that acts as a black-box retrieval proxy for model zoo. Know2Vec first accesses to models via a black-box interface in advance, capturing vital decision knowledge from models while ensuring their privacy. Next, it employs an effective encoding technique to transform the knowledge into precise model vectors. Secondly, it maps the user's query task to a knowledge vector by probing the semantic relationships within query samples. Furthermore, the proxy ensures the knowledge-consistency between query vector and model vectors within their alignment space, which is optimized through the supervised learning with diverse loss functions, and finally it can identify the most suitable model for a given task during the inference stage. Extensive experiments show that our Know2Vec achieves superior retrieval accuracy against the state-of-the-art methods in diverse neural network retrieval tasks.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1609/aaai.v39i19.34241
- https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396
- OA Status
- diamond
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409347637
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409347637Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1609/aaai.v39i19.34241Digital Object Identifier
- Title
-
Know2Vec: A Black-Box Proxy for Neural Network RetrievalWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-11Full publication date if available
- Authors
-
Z. J. Shang, Yanwei Liu, Jinxia Liu, Xiaoyan Gu, Ying Ding, Xiangyang JiList of authors in order
- Landing page
-
https://doi.org/10.1609/aaai.v39i19.34241Publisher landing page
- PDF URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
diamondOpen access status per OpenAlex
- OA URL
-
https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396Direct OA link when available
- Concepts
-
Proxy (statistics), Black box, Artificial neural network, Computer science, Artificial intelligence, Machine learningTop 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/W4409347637 |
|---|---|
| doi | https://doi.org/10.1609/aaai.v39i19.34241 |
| ids.doi | https://doi.org/10.1609/aaai.v39i19.34241 |
| ids.openalex | https://openalex.org/W4409347637 |
| fwci | 0.0 |
| type | article |
| title | Know2Vec: A Black-Box Proxy for Neural Network Retrieval |
| biblio.issue | 19 |
| biblio.volume | 39 |
| biblio.last_page | 20353 |
| biblio.first_page | 20346 |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8550999760627747 |
| 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 | Topic Modeling |
| topics[1].id | https://openalex.org/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.8273000121116638 |
| 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 | Neural Networks and Applications |
| topics[2].id | https://openalex.org/T10824 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.8149999976158142 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Image Retrieval and Classification Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780148112 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7669733762741089 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1432581 |
| concepts[0].display_name | Proxy (statistics) |
| concepts[1].id | https://openalex.org/C94966114 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6817387342453003 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q29256 |
| concepts[1].display_name | Black box |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5267198085784912 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.4927680790424347 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.298158198595047 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.1601305603981018 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| keywords[0].id | https://openalex.org/keywords/proxy |
| keywords[0].score | 0.7669733762741089 |
| keywords[0].display_name | Proxy (statistics) |
| keywords[1].id | https://openalex.org/keywords/black-box |
| keywords[1].score | 0.6817387342453003 |
| keywords[1].display_name | Black box |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.5267198085784912 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.4927680790424347 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.298158198595047 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.1601305603981018 |
| keywords[5].display_name | Machine learning |
| language | en |
| locations[0].id | doi:10.1609/aaai.v39i19.34241 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210191458 |
| locations[0].source.issn | 2159-5399, 2374-3468 |
| locations[0].source.type | conference |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2159-5399 |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].source.host_organization | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320058 |
| locations[0].source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| locations[0].license | |
| locations[0].pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396 |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.1609/aaai.v39i19.34241 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5077936254 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-4884-8129 |
| authorships[0].author.display_name | Z. J. Shang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhuoyi Shang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100720129 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-0626-1901 |
| authorships[1].author.display_name | Yanwei Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yanwei Liu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101685043 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6552-9795 |
| authorships[2].author.display_name | Jinxia Liu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Jinxia Liu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5101061961 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xiaoyan Gu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xiaoyan Gu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5072424476 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1352-1000 |
| authorships[4].author.display_name | Ying Ding |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ying Ding |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5024401174 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7333-9975 |
| authorships[5].author.display_name | Xiangyang Ji |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Xiangyang Ji |
| authorships[5].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://ojs.aaai.org/index.php/AAAI/article/download/34241/36396 |
| open_access.oa_status | diamond |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Know2Vec: A Black-Box Proxy for Neural Network Retrieval |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8550999760627747 |
| 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 | Topic Modeling |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1609/aaai.v39i19.34241 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210191458 |
| best_oa_location.source.issn | 2159-5399, 2374-3468 |
| best_oa_location.source.type | conference |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2159-5399 |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.source.host_organization | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| best_oa_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396 |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34241 |
| primary_location.id | doi:10.1609/aaai.v39i19.34241 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210191458 |
| primary_location.source.issn | 2159-5399, 2374-3468 |
| primary_location.source.type | conference |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2159-5399 |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.source.host_organization | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_name | Association for the Advancement of Artificial Intelligence |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320058 |
| primary_location.source.host_organization_lineage_names | Association for the Advancement of Artificial Intelligence |
| primary_location.license | |
| primary_location.pdf_url | https://ojs.aaai.org/index.php/AAAI/article/download/34241/36396 |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the AAAI Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.1609/aaai.v39i19.34241 |
| publication_date | 2025-04-11 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 22, 64, 104, 113, 126, 164, 212 |
| abstract_inverted_index.an | 144 |
| abstract_inverted_index.as | 112 |
| abstract_inverted_index.by | 92, 167 |
| abstract_inverted_index.in | 31, 129, 233 |
| abstract_inverted_index.is | 9, 59, 192 |
| abstract_inverted_index.it | 30, 58, 142, 157, 204 |
| abstract_inverted_index.of | 84, 99 |
| abstract_inverted_index.or | 28 |
| abstract_inverted_index.to | 20, 41, 48, 62, 68, 123, 148, 163 |
| abstract_inverted_index.we | 102 |
| abstract_inverted_index.For | 0 |
| abstract_inverted_index.and | 12, 71, 79, 184, 202 |
| abstract_inverted_index.can | 95, 205 |
| abstract_inverted_index.due | 67 |
| abstract_inverted_index.for | 25, 55, 117, 211 |
| abstract_inverted_index.our | 223 |
| abstract_inverted_index.the | 76, 82, 89, 93, 97, 150, 159, 169, 176, 179, 195, 207, 216, 230 |
| abstract_inverted_index.use | 27 |
| abstract_inverted_index.via | 125 |
| abstract_inverted_index.From | 81 |
| abstract_inverted_index.acts | 111 |
| abstract_inverted_index.find | 21 |
| abstract_inverted_index.from | 7, 135 |
| abstract_inverted_index.into | 46, 152 |
| abstract_inverted_index.loss | 200 |
| abstract_inverted_index.maps | 158 |
| abstract_inverted_index.meet | 96 |
| abstract_inverted_index.most | 208 |
| abstract_inverted_index.show | 221 |
| abstract_inverted_index.task | 162, 214 |
| abstract_inverted_index.that | 110, 222 |
| abstract_inverted_index.them | 19 |
| abstract_inverted_index.with | 198 |
| abstract_inverted_index.zoo. | 119 |
| abstract_inverted_index.zoos | 17 |
| abstract_inverted_index.Next, | 141 |
| abstract_inverted_index.avoid | 49 |
| abstract_inverted_index.first | 121 |
| abstract_inverted_index.given | 213 |
| abstract_inverted_index.i.e., | 87 |
| abstract_inverted_index.local | 33 |
| abstract_inverted_index.model | 24, 37, 56, 66, 94, 105, 118, 154, 185, 210 |
| abstract_inverted_index.named | 108 |
| abstract_inverted_index.needs | 98 |
| abstract_inverted_index.proxy | 116, 177 |
| abstract_inverted_index.query | 77, 100, 161, 173, 182 |
| abstract_inverted_index.still | 60 |
| abstract_inverted_index.their | 32, 139, 188 |
| abstract_inverted_index.vital | 132 |
| abstract_inverted_index.which | 191 |
| abstract_inverted_index.while | 137 |
| abstract_inverted_index.biased | 72 |
| abstract_inverted_index.choose | 63 |
| abstract_inverted_index.during | 215 |
| abstract_inverted_index.enable | 18 |
| abstract_inverted_index.models | 45, 124, 136 |
| abstract_inverted_index.neural | 5, 15, 43, 235 |
| abstract_inverted_index.space, | 190 |
| abstract_inverted_index.stage. | 218 |
| abstract_inverted_index.tasks, | 101 |
| abstract_inverted_index.tasks. | 238 |
| abstract_inverted_index.user's | 160 |
| abstract_inverted_index.users, | 2 |
| abstract_inverted_index.vector | 166, 183 |
| abstract_inverted_index.within | 172, 187 |
| abstract_inverted_index.against | 229 |
| abstract_inverted_index.attempt | 40 |
| abstract_inverted_index.between | 75, 181 |
| abstract_inverted_index.complex | 50 |
| abstract_inverted_index.convert | 42 |
| abstract_inverted_index.current | 36 |
| abstract_inverted_index.dataset | 78 |
| abstract_inverted_index.diverse | 199, 234 |
| abstract_inverted_index.employs | 143 |
| abstract_inverted_index.ensures | 178 |
| abstract_inverted_index.finally | 203 |
| abstract_inverted_index.general | 1 |
| abstract_inverted_index.methods | 232 |
| abstract_inverted_index.models. | 80 |
| abstract_inverted_index.network | 6, 16, 44, 236 |
| abstract_inverted_index.precise | 153 |
| abstract_inverted_index.probing | 168 |
| abstract_inverted_index.propose | 103 |
| abstract_inverted_index.scheme, | 107 |
| abstract_inverted_index.scratch | 8 |
| abstract_inverted_index.through | 194 |
| abstract_inverted_index.usually | 10 |
| abstract_inverted_index.vectors | 47, 186 |
| abstract_inverted_index.whether | 88 |
| abstract_inverted_index.Although | 35 |
| abstract_inverted_index.Know2Vec | 120, 224 |
| abstract_inverted_index.accesses | 122 |
| abstract_inverted_index.accuracy | 228 |
| abstract_inverted_index.achieves | 225 |
| abstract_inverted_index.advance, | 130 |
| abstract_inverted_index.decision | 133 |
| abstract_inverted_index.directly | 26 |
| abstract_inverted_index.encoding | 146 |
| abstract_inverted_index.ensuring | 138 |
| abstract_inverted_index.identify | 206 |
| abstract_inverted_index.learning | 197 |
| abstract_inverted_index.multiple | 51 |
| abstract_inverted_index.privacy. | 140 |
| abstract_inverted_index.required | 54 |
| abstract_inverted_index.samples. | 174 |
| abstract_inverted_index.semantic | 170 |
| abstract_inverted_index.suitable | 65, 209 |
| abstract_inverted_index.superior | 226 |
| abstract_inverted_index.training | 3 |
| abstract_inverted_index.vectors. | 155 |
| abstract_inverted_index.Extensive | 219 |
| abstract_inverted_index.Know2Vec, | 109 |
| abstract_inverted_index.Secondly, | 156 |
| abstract_inverted_index.alignment | 74, 189 |
| abstract_inverted_index.black-box | 114, 127 |
| abstract_inverted_index.capturing | 131 |
| abstract_inverted_index.difficult | 61 |
| abstract_inverted_index.effective | 145 |
| abstract_inverted_index.inference | 52, 217 |
| abstract_inverted_index.interface | 128 |
| abstract_inverted_index.knowledge | 85, 90, 134, 151, 165 |
| abstract_inverted_index.optimized | 193 |
| abstract_inverted_index.possessed | 91 |
| abstract_inverted_index.processes | 53 |
| abstract_inverted_index.retrieval | 38, 106, 115, 227, 237 |
| abstract_inverted_index.solutions | 39 |
| abstract_inverted_index.technique | 147 |
| abstract_inverted_index.transform | 149 |
| abstract_inverted_index.functions, | 201 |
| abstract_inverted_index.inaccurate | 69 |
| abstract_inverted_index.selection, | 57 |
| abstract_inverted_index.supervised | 196 |
| abstract_inverted_index.challenging | 11 |
| abstract_inverted_index.correlation | 73 |
| abstract_inverted_index.experiments | 220 |
| abstract_inverted_index.fine-tuning | 29 |
| abstract_inverted_index.perspective | 83 |
| abstract_inverted_index.Fortunately, | 14 |
| abstract_inverted_index.Furthermore, | 175 |
| abstract_inverted_index.consistency, | 86 |
| abstract_inverted_index.environments. | 34 |
| abstract_inverted_index.relationships | 171 |
| abstract_inverted_index.vectorization | 70 |
| abstract_inverted_index.well-performing | 23 |
| abstract_inverted_index.labor-intensive. | 13 |
| abstract_inverted_index.state-of-the-art | 231 |
| abstract_inverted_index.knowledge-consistency | 180 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.08341709 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |