Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference Article Swipe
Souvik Kundu
,
Shunlin Lu
,
Yuke Zhang
,
Jacqueline Liu
,
Peter A. Beerel
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2301.09254
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2301.09254
The large number of ReLU non-linearity operations in existing deep neural networks makes them ill-suited for latency-efficient private inference (PI). Existing techniques to reduce ReLU operations often involve manual effort and sacrifice significant accuracy. In this paper, we first present a novel measure of non-linearity layers' ReLU sensitivity, enabling mitigation of the time-consuming manual efforts in identifying the same. Based on this sensitivity, we then present SENet, a three-stage training method that for a given ReLU budget, automatically assigns per-layer ReLU counts, decides the ReLU locations for each layer's activation map, and trains a model with significantly fewer ReLUs to potentially yield latency and communication efficient PI. Experimental evaluations with multiple models on various datasets show SENet's superior performance both in terms of reduced ReLUs and improved classification accuracy compared to existing alternatives. In particular, SENet can yield models that require up to ~2x fewer ReLUs while yielding similar accuracy. For a similar ReLU budget SENet can yield models with ~2.32% improved classification accuracy, evaluated on CIFAR-100.
Related Topics
Concepts
Computer science
Inference
Latency (audio)
Linearity
Artificial neural network
Deep neural networks
Sensitivity (control systems)
Artificial intelligence
Deep learning
Machine learning
Layer (electronics)
Data mining
Engineering
Electronic engineering
Chemistry
Organic chemistry
Telecommunications
Electrical engineering
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2301.09254
- https://arxiv.org/pdf/2301.09254
- OA Status
- green
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4317940589
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4317940589Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2301.09254Digital Object Identifier
- Title
-
Learning to Linearize Deep Neural Networks for Secure and Efficient Private InferenceWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-01-23Full publication date if available
- Authors
-
Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Liu, Peter A. BeerelList of authors in order
- Landing page
-
https://arxiv.org/abs/2301.09254Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2301.09254Direct 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/2301.09254Direct OA link when available
- Concepts
-
Computer science, Inference, Latency (audio), Linearity, Artificial neural network, Deep neural networks, Sensitivity (control systems), Artificial intelligence, Deep learning, Machine learning, Layer (electronics), Data mining, Engineering, Electronic engineering, Chemistry, Organic chemistry, Telecommunications, Electrical engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 1, 2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4317940589 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2301.09254 |
| ids.doi | https://doi.org/10.48550/arxiv.2301.09254 |
| ids.openalex | https://openalex.org/W4317940589 |
| fwci | |
| type | preprint |
| title | Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998000264167786 |
| 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 | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T10764 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9987999796867371 |
| 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 | Privacy-Preserving Technologies in Data |
| topics[2].id | https://openalex.org/T11612 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.996399998664856 |
| 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 | Stochastic Gradient Optimization Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.722395658493042 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2776214188 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7171061038970947 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[1].display_name | Inference |
| concepts[2].id | https://openalex.org/C82876162 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6678021550178528 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17096504 |
| concepts[2].display_name | Latency (audio) |
| concepts[3].id | https://openalex.org/C77170095 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6451054811477661 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1753188 |
| concepts[3].display_name | Linearity |
| concepts[4].id | https://openalex.org/C50644808 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6243008971214294 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[4].display_name | Artificial neural network |
| concepts[5].id | https://openalex.org/C2984842247 |
| concepts[5].level | 3 |
| concepts[5].score | 0.5955281257629395 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[5].display_name | Deep neural networks |
| concepts[6].id | https://openalex.org/C21200559 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5612812638282776 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7451068 |
| concepts[6].display_name | Sensitivity (control systems) |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.5412838459014893 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C108583219 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4793044626712799 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[8].display_name | Deep learning |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.44093209505081177 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C2779227376 |
| concepts[10].level | 2 |
| concepts[10].score | 0.41665828227996826 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q6505497 |
| concepts[10].display_name | Layer (electronics) |
| concepts[11].id | https://openalex.org/C124101348 |
| concepts[11].level | 1 |
| concepts[11].score | 0.33287179470062256 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[11].display_name | Data mining |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.08817940950393677 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C24326235 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q126095 |
| concepts[13].display_name | Electronic engineering |
| concepts[14].id | https://openalex.org/C185592680 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[14].display_name | Chemistry |
| concepts[15].id | https://openalex.org/C178790620 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[15].display_name | Organic chemistry |
| concepts[16].id | https://openalex.org/C76155785 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[16].display_name | Telecommunications |
| concepts[17].id | https://openalex.org/C119599485 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q43035 |
| concepts[17].display_name | Electrical engineering |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.722395658493042 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/inference |
| keywords[1].score | 0.7171061038970947 |
| keywords[1].display_name | Inference |
| keywords[2].id | https://openalex.org/keywords/latency |
| keywords[2].score | 0.6678021550178528 |
| keywords[2].display_name | Latency (audio) |
| keywords[3].id | https://openalex.org/keywords/linearity |
| keywords[3].score | 0.6451054811477661 |
| keywords[3].display_name | Linearity |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.6243008971214294 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[5].score | 0.5955281257629395 |
| keywords[5].display_name | Deep neural networks |
| keywords[6].id | https://openalex.org/keywords/sensitivity |
| keywords[6].score | 0.5612812638282776 |
| keywords[6].display_name | Sensitivity (control systems) |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.5412838459014893 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/deep-learning |
| keywords[8].score | 0.4793044626712799 |
| keywords[8].display_name | Deep learning |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.44093209505081177 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/layer |
| keywords[10].score | 0.41665828227996826 |
| keywords[10].display_name | Layer (electronics) |
| keywords[11].id | https://openalex.org/keywords/data-mining |
| keywords[11].score | 0.33287179470062256 |
| keywords[11].display_name | Data mining |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.08817940950393677 |
| keywords[12].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2301.09254 |
| 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/2301.09254 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2301.09254 |
| locations[1].id | doi:10.48550/arxiv.2301.09254 |
| 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.2301.09254 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5087095284 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-5815-8765 |
| authorships[0].author.display_name | Souvik Kundu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Kundu, Souvik |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5028455158 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Shunlin Lu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lu, Shunlin |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5019021341 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-5253-5478 |
| authorships[2].author.display_name | Yuke Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Yuke |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5102663291 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Jacqueline Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Liu, Jacqueline |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5084205024 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8283-0168 |
| authorships[4].author.display_name | Peter A. Beerel |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Beerel, Peter A. |
| authorships[4].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/2301.09254 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998000264167786 |
| 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 | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W3008625068, https://openalex.org/W3128807919, https://openalex.org/W3176411177, https://openalex.org/W3035501883, https://openalex.org/W4377865163, https://openalex.org/W3042419602, https://openalex.org/W2966649771, https://openalex.org/W3193857078, https://openalex.org/W2888956734, https://openalex.org/W3000197790 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 1 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2301.09254 |
| 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/2301.09254 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2301.09254 |
| primary_location.id | pmh:oai:arXiv.org:2301.09254 |
| 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/2301.09254 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2301.09254 |
| publication_date | 2023-01-23 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 40, 67, 73, 93, 151 |
| abstract_inverted_index.In | 34, 133 |
| abstract_inverted_index.in | 7, 55, 120 |
| abstract_inverted_index.of | 3, 43, 50, 122 |
| abstract_inverted_index.on | 60, 112, 165 |
| abstract_inverted_index.to | 22, 99, 130, 142 |
| abstract_inverted_index.up | 141 |
| abstract_inverted_index.we | 37, 63 |
| abstract_inverted_index.For | 150 |
| abstract_inverted_index.PI. | 106 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 30, 91, 103, 125 |
| abstract_inverted_index.can | 136, 156 |
| abstract_inverted_index.for | 15, 72, 86 |
| abstract_inverted_index.the | 51, 57, 83 |
| abstract_inverted_index.~2x | 143 |
| abstract_inverted_index.ReLU | 4, 24, 46, 75, 80, 84, 153 |
| abstract_inverted_index.both | 119 |
| abstract_inverted_index.deep | 9 |
| abstract_inverted_index.each | 87 |
| abstract_inverted_index.map, | 90 |
| abstract_inverted_index.show | 115 |
| abstract_inverted_index.that | 71, 139 |
| abstract_inverted_index.them | 13 |
| abstract_inverted_index.then | 64 |
| abstract_inverted_index.this | 35, 61 |
| abstract_inverted_index.with | 95, 109, 159 |
| abstract_inverted_index.(PI). | 19 |
| abstract_inverted_index.Based | 59 |
| abstract_inverted_index.ReLUs | 98, 124, 145 |
| abstract_inverted_index.SENet | 135, 155 |
| abstract_inverted_index.fewer | 97, 144 |
| abstract_inverted_index.first | 38 |
| abstract_inverted_index.given | 74 |
| abstract_inverted_index.large | 1 |
| abstract_inverted_index.makes | 12 |
| abstract_inverted_index.model | 94 |
| abstract_inverted_index.novel | 41 |
| abstract_inverted_index.often | 26 |
| abstract_inverted_index.same. | 58 |
| abstract_inverted_index.terms | 121 |
| abstract_inverted_index.while | 146 |
| abstract_inverted_index.yield | 101, 137, 157 |
| abstract_inverted_index.SENet, | 66 |
| abstract_inverted_index.budget | 154 |
| abstract_inverted_index.effort | 29 |
| abstract_inverted_index.manual | 28, 53 |
| abstract_inverted_index.method | 70 |
| abstract_inverted_index.models | 111, 138, 158 |
| abstract_inverted_index.neural | 10 |
| abstract_inverted_index.number | 2 |
| abstract_inverted_index.paper, | 36 |
| abstract_inverted_index.reduce | 23 |
| abstract_inverted_index.trains | 92 |
| abstract_inverted_index.~2.32% | 160 |
| abstract_inverted_index.SENet's | 116 |
| abstract_inverted_index.assigns | 78 |
| abstract_inverted_index.budget, | 76 |
| abstract_inverted_index.counts, | 81 |
| abstract_inverted_index.decides | 82 |
| abstract_inverted_index.efforts | 54 |
| abstract_inverted_index.involve | 27 |
| abstract_inverted_index.latency | 102 |
| abstract_inverted_index.layer's | 88 |
| abstract_inverted_index.layers' | 45 |
| abstract_inverted_index.measure | 42 |
| abstract_inverted_index.present | 39, 65 |
| abstract_inverted_index.private | 17 |
| abstract_inverted_index.reduced | 123 |
| abstract_inverted_index.require | 140 |
| abstract_inverted_index.similar | 148, 152 |
| abstract_inverted_index.various | 113 |
| abstract_inverted_index.Existing | 20 |
| abstract_inverted_index.accuracy | 128 |
| abstract_inverted_index.compared | 129 |
| abstract_inverted_index.datasets | 114 |
| abstract_inverted_index.enabling | 48 |
| abstract_inverted_index.existing | 8, 131 |
| abstract_inverted_index.improved | 126, 161 |
| abstract_inverted_index.multiple | 110 |
| abstract_inverted_index.networks | 11 |
| abstract_inverted_index.superior | 117 |
| abstract_inverted_index.training | 69 |
| abstract_inverted_index.yielding | 147 |
| abstract_inverted_index.accuracy, | 163 |
| abstract_inverted_index.accuracy. | 33, 149 |
| abstract_inverted_index.efficient | 105 |
| abstract_inverted_index.evaluated | 164 |
| abstract_inverted_index.inference | 18 |
| abstract_inverted_index.locations | 85 |
| abstract_inverted_index.per-layer | 79 |
| abstract_inverted_index.sacrifice | 31 |
| abstract_inverted_index.CIFAR-100. | 166 |
| abstract_inverted_index.activation | 89 |
| abstract_inverted_index.ill-suited | 14 |
| abstract_inverted_index.mitigation | 49 |
| abstract_inverted_index.operations | 6, 25 |
| abstract_inverted_index.techniques | 21 |
| abstract_inverted_index.evaluations | 108 |
| abstract_inverted_index.identifying | 56 |
| abstract_inverted_index.particular, | 134 |
| abstract_inverted_index.performance | 118 |
| abstract_inverted_index.potentially | 100 |
| abstract_inverted_index.significant | 32 |
| abstract_inverted_index.three-stage | 68 |
| abstract_inverted_index.Experimental | 107 |
| abstract_inverted_index.sensitivity, | 47, 62 |
| abstract_inverted_index.alternatives. | 132 |
| abstract_inverted_index.automatically | 77 |
| abstract_inverted_index.communication | 104 |
| abstract_inverted_index.non-linearity | 5, 44 |
| abstract_inverted_index.significantly | 96 |
| abstract_inverted_index.classification | 127, 162 |
| abstract_inverted_index.time-consuming | 52 |
| abstract_inverted_index.latency-efficient | 16 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/17 |
| sustainable_development_goals[0].score | 0.5 |
| sustainable_development_goals[0].display_name | Partnerships for the goals |
| citation_normalized_percentile |