DistDNAS: Search Efficient Feature Interactions within 2 Hours Article Swipe
Tunhou Zhang
,
Wei Wen
,
Igor Fedorov
,
Xi Liu
,
Buyun Zhang
,
Fangqiu Han
,
Wen-Yen Chen
,
Yiping Han
,
Feng Yan
,
Hai Li
,
Yiran Chen
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2311.00231
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2311.00231
Search efficiency and serving efficiency are two major axes in building feature interactions and expediting the model development process in recommender systems. On large-scale benchmarks, searching for the optimal feature interaction design requires extensive cost due to the sequential workflow on the large volume of data. In addition, fusing interactions of various sources, orders, and mathematical operations introduces potential conflicts and additional redundancy toward recommender models, leading to sub-optimal trade-offs in performance and serving cost. In this paper, we present DistDNAS as a neat solution to brew swift and efficient feature interaction design. DistDNAS proposes a supernet to incorporate interaction modules of varying orders and types as a search space. To optimize search efficiency, DistDNAS distributes the search and aggregates the choice of optimal interaction modules on varying data dates, achieving over 25x speed-up and reducing search cost from 2 days to 2 hours. To optimize serving efficiency, DistDNAS introduces a differentiable cost-aware loss to penalize the selection of redundant interaction modules, enhancing the efficiency of discovered feature interactions in serving. We extensively evaluate the best models crafted by DistDNAS on a 1TB Criteo Terabyte dataset. Experimental evaluations demonstrate 0.001 AUC improvement and 60% FLOPs saving over current state-of-the-art CTR models.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2311.00231
- https://arxiv.org/pdf/2311.00231
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4388275307
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4388275307Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2311.00231Digital Object Identifier
- Title
-
DistDNAS: Search Efficient Feature Interactions within 2 HoursWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-11-01Full publication date if available
- Authors
-
Tunhou Zhang, Wei Wen, Igor Fedorov, Xi Liu, Buyun Zhang, Fangqiu Han, Wen-Yen Chen, Yiping Han, Feng Yan, Hai Li, Yiran ChenList of authors in order
- Landing page
-
https://arxiv.org/abs/2311.00231Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2311.00231Direct 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/2311.00231Direct OA link when available
- Concepts
-
Computer science, Expediting, Workflow, Redundancy (engineering), Feature (linguistics), Churning, Terabyte, Artificial intelligence, Data mining, Database, Engineering, Systems engineering, Economics, Operating system, Philosophy, Labour economics, LinguisticsTop 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/W4388275307 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2311.00231 |
| ids.doi | https://doi.org/10.48550/arxiv.2311.00231 |
| ids.openalex | https://openalex.org/W4388275307 |
| fwci | 0.0 |
| type | preprint |
| title | DistDNAS: Search Efficient Feature Interactions within 2 Hours |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10627 |
| 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/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Image and Video Retrieval Techniques |
| topics[1].id | https://openalex.org/T11439 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9965000152587891 |
| 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 | Video Analysis and Summarization |
| topics[2].id | https://openalex.org/T10203 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9955999851226807 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1710 |
| topics[2].subfield.display_name | Information Systems |
| topics[2].display_name | Recommender Systems and Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7537058591842651 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C134448949 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6707268953323364 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1384274 |
| concepts[1].display_name | Expediting |
| concepts[2].id | https://openalex.org/C177212765 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6580596566200256 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q627335 |
| concepts[2].display_name | Workflow |
| concepts[3].id | https://openalex.org/C152124472 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5797975063323975 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1204361 |
| concepts[3].display_name | Redundancy (engineering) |
| concepts[4].id | https://openalex.org/C2776401178 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5431082248687744 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[4].display_name | Feature (linguistics) |
| concepts[5].id | https://openalex.org/C161664118 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5314276218414307 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1089933 |
| concepts[5].display_name | Churning |
| concepts[6].id | https://openalex.org/C199683683 |
| concepts[6].level | 2 |
| concepts[6].score | 0.44959723949432373 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8799 |
| concepts[6].display_name | Terabyte |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.33634254336357117 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C124101348 |
| concepts[8].level | 1 |
| concepts[8].score | 0.33022546768188477 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[8].display_name | Data mining |
| concepts[9].id | https://openalex.org/C77088390 |
| concepts[9].level | 1 |
| concepts[9].score | 0.1702595353126526 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8513 |
| concepts[9].display_name | Database |
| concepts[10].id | https://openalex.org/C127413603 |
| concepts[10].level | 0 |
| concepts[10].score | 0.12245625257492065 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[10].display_name | Engineering |
| concepts[11].id | https://openalex.org/C201995342 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[11].display_name | Systems engineering |
| concepts[12].id | https://openalex.org/C162324750 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8134 |
| concepts[12].display_name | Economics |
| concepts[13].id | https://openalex.org/C111919701 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[13].display_name | Operating system |
| concepts[14].id | https://openalex.org/C138885662 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[14].display_name | Philosophy |
| concepts[15].id | https://openalex.org/C145236788 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q28161 |
| concepts[15].display_name | Labour economics |
| concepts[16].id | https://openalex.org/C41895202 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[16].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7537058591842651 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/expediting |
| keywords[1].score | 0.6707268953323364 |
| keywords[1].display_name | Expediting |
| keywords[2].id | https://openalex.org/keywords/workflow |
| keywords[2].score | 0.6580596566200256 |
| keywords[2].display_name | Workflow |
| keywords[3].id | https://openalex.org/keywords/redundancy |
| keywords[3].score | 0.5797975063323975 |
| keywords[3].display_name | Redundancy (engineering) |
| keywords[4].id | https://openalex.org/keywords/feature |
| keywords[4].score | 0.5431082248687744 |
| keywords[4].display_name | Feature (linguistics) |
| keywords[5].id | https://openalex.org/keywords/churning |
| keywords[5].score | 0.5314276218414307 |
| keywords[5].display_name | Churning |
| keywords[6].id | https://openalex.org/keywords/terabyte |
| keywords[6].score | 0.44959723949432373 |
| keywords[6].display_name | Terabyte |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.33634254336357117 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/data-mining |
| keywords[8].score | 0.33022546768188477 |
| keywords[8].display_name | Data mining |
| keywords[9].id | https://openalex.org/keywords/database |
| keywords[9].score | 0.1702595353126526 |
| keywords[9].display_name | Database |
| keywords[10].id | https://openalex.org/keywords/engineering |
| keywords[10].score | 0.12245625257492065 |
| keywords[10].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2311.00231 |
| 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/2311.00231 |
| 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/2311.00231 |
| locations[1].id | doi:10.48550/arxiv.2311.00231 |
| 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-journal |
| 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.2311.00231 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5052236334 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9590-9433 |
| authorships[0].author.display_name | Tunhou Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhang, Tunhou |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100396390 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-2753-3870 |
| authorships[1].author.display_name | Wei Wen |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wen, Wei |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5056063665 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-7235-4823 |
| authorships[2].author.display_name | Igor Fedorov |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Fedorov, Igor |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5105370352 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xi Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Liu, Xi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5047533043 |
| authorships[4].author.orcid | https://orcid.org/0009-0007-9053-4661 |
| authorships[4].author.display_name | Buyun Zhang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhang, Buyun |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5013081925 |
| authorships[5].author.orcid | https://orcid.org/0009-0006-0309-7284 |
| authorships[5].author.display_name | Fangqiu Han |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Han, Fangqiu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5032809354 |
| authorships[6].author.orcid | https://orcid.org/0009-0004-9371-5642 |
| authorships[6].author.display_name | Wen-Yen Chen |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Chen, Wen-Yen |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5100537435 |
| authorships[7].author.orcid | https://orcid.org/0009-0001-1300-1315 |
| authorships[7].author.display_name | Yiping Han |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Han, Yiping |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5100381152 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-9840-7754 |
| authorships[8].author.display_name | Feng Yan |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Yan, Feng |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5100429403 |
| authorships[9].author.orcid | https://orcid.org/0000-0003-3228-6544 |
| authorships[9].author.display_name | Hai Li |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Li, Hai |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5058073627 |
| authorships[10].author.orcid | https://orcid.org/0000-0002-1486-8412 |
| authorships[10].author.display_name | Yiran Chen |
| authorships[10].author_position | last |
| authorships[10].raw_author_name | Chen, Yiran |
| authorships[10].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/2311.00231 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | DistDNAS: Search Efficient Feature Interactions within 2 Hours |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10627 |
| 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/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Image and Video Retrieval Techniques |
| related_works | https://openalex.org/W2085395339, https://openalex.org/W2024632604, https://openalex.org/W2071999521, https://openalex.org/W2068005943, https://openalex.org/W2010478499, https://openalex.org/W4317792299, https://openalex.org/W2050011582, https://openalex.org/W2071715249, https://openalex.org/W2051220639, https://openalex.org/W2091881573 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2311.00231 |
| 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/2311.00231 |
| 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/2311.00231 |
| primary_location.id | pmh:oai:arXiv.org:2311.00231 |
| 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/2311.00231 |
| 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/2311.00231 |
| publication_date | 2023-11-01 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.2 | 139, 142 |
| abstract_inverted_index.a | 82, 95, 107, 150, 181 |
| abstract_inverted_index.In | 46, 75 |
| abstract_inverted_index.On | 22 |
| abstract_inverted_index.To | 110, 144 |
| abstract_inverted_index.We | 171 |
| abstract_inverted_index.as | 81, 106 |
| abstract_inverted_index.by | 178 |
| abstract_inverted_index.in | 9, 19, 70, 169 |
| abstract_inverted_index.of | 44, 50, 101, 122, 158, 165 |
| abstract_inverted_index.on | 40, 126, 180 |
| abstract_inverted_index.to | 36, 67, 85, 97, 141, 154 |
| abstract_inverted_index.we | 78 |
| abstract_inverted_index.1TB | 182 |
| abstract_inverted_index.25x | 132 |
| abstract_inverted_index.60% | 193 |
| abstract_inverted_index.AUC | 190 |
| abstract_inverted_index.CTR | 199 |
| abstract_inverted_index.and | 2, 13, 54, 60, 72, 88, 104, 118, 134, 192 |
| abstract_inverted_index.are | 5 |
| abstract_inverted_index.due | 35 |
| abstract_inverted_index.for | 26 |
| abstract_inverted_index.the | 15, 27, 37, 41, 116, 120, 156, 163, 174 |
| abstract_inverted_index.two | 6 |
| abstract_inverted_index.axes | 8 |
| abstract_inverted_index.best | 175 |
| abstract_inverted_index.brew | 86 |
| abstract_inverted_index.cost | 34, 137 |
| abstract_inverted_index.data | 128 |
| abstract_inverted_index.days | 140 |
| abstract_inverted_index.from | 138 |
| abstract_inverted_index.loss | 153 |
| abstract_inverted_index.neat | 83 |
| abstract_inverted_index.over | 131, 196 |
| abstract_inverted_index.this | 76 |
| abstract_inverted_index.0.001 | 189 |
| abstract_inverted_index.FLOPs | 194 |
| abstract_inverted_index.cost. | 74 |
| abstract_inverted_index.data. | 45 |
| abstract_inverted_index.large | 42 |
| abstract_inverted_index.major | 7 |
| abstract_inverted_index.model | 16 |
| abstract_inverted_index.swift | 87 |
| abstract_inverted_index.types | 105 |
| abstract_inverted_index.Criteo | 183 |
| abstract_inverted_index.Search | 0 |
| abstract_inverted_index.choice | 121 |
| abstract_inverted_index.dates, | 129 |
| abstract_inverted_index.design | 31 |
| abstract_inverted_index.fusing | 48 |
| abstract_inverted_index.hours. | 143 |
| abstract_inverted_index.models | 176 |
| abstract_inverted_index.orders | 103 |
| abstract_inverted_index.paper, | 77 |
| abstract_inverted_index.saving | 195 |
| abstract_inverted_index.search | 108, 112, 117, 136 |
| abstract_inverted_index.space. | 109 |
| abstract_inverted_index.toward | 63 |
| abstract_inverted_index.volume | 43 |
| abstract_inverted_index.crafted | 177 |
| abstract_inverted_index.current | 197 |
| abstract_inverted_index.design. | 92 |
| abstract_inverted_index.feature | 11, 29, 90, 167 |
| abstract_inverted_index.leading | 66 |
| abstract_inverted_index.models, | 65 |
| abstract_inverted_index.models. | 200 |
| abstract_inverted_index.modules | 100, 125 |
| abstract_inverted_index.optimal | 28, 123 |
| abstract_inverted_index.orders, | 53 |
| abstract_inverted_index.present | 79 |
| abstract_inverted_index.process | 18 |
| abstract_inverted_index.serving | 3, 73, 146 |
| abstract_inverted_index.various | 51 |
| abstract_inverted_index.varying | 102, 127 |
| abstract_inverted_index.DistDNAS | 80, 93, 114, 148, 179 |
| abstract_inverted_index.Terabyte | 184 |
| abstract_inverted_index.building | 10 |
| abstract_inverted_index.dataset. | 185 |
| abstract_inverted_index.evaluate | 173 |
| abstract_inverted_index.modules, | 161 |
| abstract_inverted_index.optimize | 111, 145 |
| abstract_inverted_index.penalize | 155 |
| abstract_inverted_index.proposes | 94 |
| abstract_inverted_index.reducing | 135 |
| abstract_inverted_index.requires | 32 |
| abstract_inverted_index.serving. | 170 |
| abstract_inverted_index.solution | 84 |
| abstract_inverted_index.sources, | 52 |
| abstract_inverted_index.speed-up | 133 |
| abstract_inverted_index.supernet | 96 |
| abstract_inverted_index.systems. | 21 |
| abstract_inverted_index.workflow | 39 |
| abstract_inverted_index.achieving | 130 |
| abstract_inverted_index.addition, | 47 |
| abstract_inverted_index.conflicts | 59 |
| abstract_inverted_index.efficient | 89 |
| abstract_inverted_index.enhancing | 162 |
| abstract_inverted_index.extensive | 33 |
| abstract_inverted_index.potential | 58 |
| abstract_inverted_index.redundant | 159 |
| abstract_inverted_index.searching | 25 |
| abstract_inverted_index.selection | 157 |
| abstract_inverted_index.additional | 61 |
| abstract_inverted_index.aggregates | 119 |
| abstract_inverted_index.cost-aware | 152 |
| abstract_inverted_index.discovered | 166 |
| abstract_inverted_index.efficiency | 1, 4, 164 |
| abstract_inverted_index.expediting | 14 |
| abstract_inverted_index.introduces | 57, 149 |
| abstract_inverted_index.operations | 56 |
| abstract_inverted_index.redundancy | 62 |
| abstract_inverted_index.sequential | 38 |
| abstract_inverted_index.trade-offs | 69 |
| abstract_inverted_index.benchmarks, | 24 |
| abstract_inverted_index.demonstrate | 188 |
| abstract_inverted_index.development | 17 |
| abstract_inverted_index.distributes | 115 |
| abstract_inverted_index.efficiency, | 113, 147 |
| abstract_inverted_index.evaluations | 187 |
| abstract_inverted_index.extensively | 172 |
| abstract_inverted_index.improvement | 191 |
| abstract_inverted_index.incorporate | 98 |
| abstract_inverted_index.interaction | 30, 91, 99, 124, 160 |
| abstract_inverted_index.large-scale | 23 |
| abstract_inverted_index.performance | 71 |
| abstract_inverted_index.recommender | 20, 64 |
| abstract_inverted_index.sub-optimal | 68 |
| abstract_inverted_index.Experimental | 186 |
| abstract_inverted_index.interactions | 12, 49, 168 |
| abstract_inverted_index.mathematical | 55 |
| abstract_inverted_index.differentiable | 151 |
| abstract_inverted_index.state-of-the-art | 198 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 11 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/9 |
| sustainable_development_goals[0].score | 0.41999998688697815 |
| sustainable_development_goals[0].display_name | Industry, innovation and infrastructure |
| citation_normalized_percentile.value | 0.16832366 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |