Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning Article Swipe
Chen Zhao
,
Shuming Liu
,
Karttikeya Mangalam
,
Guocheng Qian
,
Fatimah Zohra
,
Abdulmohsen Alghannam
,
Jitendra Malik
,
Bernard Ghanem
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.04105
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.04105
Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memory-intensive for tasks with high-resolution data, e.g., video understanding, small object detection, and point cloud analysis. In this paper, we propose Dynamic Reversible Dual-Residual Networks, or Dr$^2$Net, a novel family of network architectures that acts as a surrogate network to finetune a pretrained model with substantially reduced memory consumption. Dr$^2$Net contains two types of residual connections, one maintaining the residual structure in the pretrained models, and the other making the network reversible. Due to its reversibility, intermediate activations, which can be reconstructed from output, are cleared from memory during training. We use two coefficients on either type of residual connections respectively, and introduce a dynamic training strategy that seamlessly transitions the pretrained model to a reversible network with much higher numerical precision. We evaluate Dr$^2$Net on various pretrained models and various tasks, and show that it can reach comparable performance to conventional finetuning but with significantly less memory usage.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2401.04105
- https://arxiv.org/pdf/2401.04105
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4390723204
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4390723204Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2401.04105Digital Object Identifier
- Title
-
Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient FinetuningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-08Full publication date if available
- Authors
-
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard GhanemList of authors in order
- Landing page
-
https://arxiv.org/abs/2401.04105Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2401.04105Direct 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/2401.04105Direct OA link when available
- Concepts
-
Residual, Computer science, Clearance, Net (polyhedron), Dual (grammatical number), Artificial intelligence, Algorithm, Art, Medicine, Geometry, Literature, Mathematics, UrologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4390723204 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2401.04105 |
| ids.doi | https://doi.org/10.48550/arxiv.2401.04105 |
| ids.openalex | https://openalex.org/W4390723204 |
| fwci | 0.53015756 |
| type | preprint |
| title | Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9994999766349792 |
| 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 Neural Network Applications |
| topics[1].id | https://openalex.org/T10812 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9900000095367432 |
| 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 | Human Pose and Action Recognition |
| topics[2].id | https://openalex.org/T11689 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.975600004196167 |
| 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 | Adversarial Robustness in Machine Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C155512373 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8582794666290283 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q287450 |
| concepts[0].display_name | Residual |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8316748142242432 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C138944611 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6160569190979004 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1163287 |
| concepts[2].display_name | Clearance |
| concepts[3].id | https://openalex.org/C14166107 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5576462745666504 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q253829 |
| concepts[3].display_name | Net (polyhedron) |
| concepts[4].id | https://openalex.org/C2780980858 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5263946056365967 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q110022 |
| concepts[4].display_name | Dual (grammatical number) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.45630592107772827 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C11413529 |
| concepts[6].level | 1 |
| concepts[6].score | 0.2329431176185608 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[6].display_name | Algorithm |
| concepts[7].id | https://openalex.org/C142362112 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[7].display_name | Art |
| concepts[8].id | https://openalex.org/C71924100 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[8].display_name | Medicine |
| concepts[9].id | https://openalex.org/C2524010 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[9].display_name | Geometry |
| concepts[10].id | https://openalex.org/C124952713 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8242 |
| concepts[10].display_name | Literature |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C126894567 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q105650 |
| concepts[12].display_name | Urology |
| keywords[0].id | https://openalex.org/keywords/residual |
| keywords[0].score | 0.8582794666290283 |
| keywords[0].display_name | Residual |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8316748142242432 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/clearance |
| keywords[2].score | 0.6160569190979004 |
| keywords[2].display_name | Clearance |
| keywords[3].id | https://openalex.org/keywords/net |
| keywords[3].score | 0.5576462745666504 |
| keywords[3].display_name | Net (polyhedron) |
| keywords[4].id | https://openalex.org/keywords/dual |
| keywords[4].score | 0.5263946056365967 |
| keywords[4].display_name | Dual (grammatical number) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.45630592107772827 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/algorithm |
| keywords[6].score | 0.2329431176185608 |
| keywords[6].display_name | Algorithm |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2401.04105 |
| 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/2401.04105 |
| 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/2401.04105 |
| locations[1].id | doi:10.48550/arxiv.2401.04105 |
| 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.2401.04105 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100351992 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9843-6758 |
| authorships[0].author.display_name | Chen Zhao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhao, Chen |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100664295 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4949-4318 |
| authorships[1].author.display_name | Shuming Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liu, Shuming |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5038469427 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2169-1395 |
| authorships[2].author.display_name | Karttikeya Mangalam |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Mangalam, Karttikeya |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5032922702 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2935-8570 |
| authorships[3].author.display_name | Guocheng Qian |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Qian, Guocheng |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5093701194 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Fatimah Zohra |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zohra, Fatimah |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5000239291 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Abdulmohsen Alghannam |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Alghannam, Abdulmohsen |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5001594573 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-3695-1580 |
| authorships[6].author.display_name | Jitendra Malik |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Malik, Jitendra |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5024763828 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-5534-587X |
| authorships[7].author.display_name | Bernard Ghanem |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Ghanem, Bernard |
| authorships[7].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/2401.04105 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-01-13T00:00:00 |
| display_name | Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9994999766349792 |
| 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 Neural Network Applications |
| related_works | https://openalex.org/W94007947, https://openalex.org/W4386603341, https://openalex.org/W1972144726, https://openalex.org/W3176776294, https://openalex.org/W2193407120, https://openalex.org/W4250433556, https://openalex.org/W2617112367, https://openalex.org/W3165156588, https://openalex.org/W1965612393, https://openalex.org/W4253730245 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2401.04105 |
| 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/2401.04105 |
| 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/2401.04105 |
| primary_location.id | pmh:oai:arXiv.org:2401.04105 |
| 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/2401.04105 |
| 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/2401.04105 |
| publication_date | 2024-01-08 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 52, 61, 66, 128, 139 |
| abstract_inverted_index.In | 41 |
| abstract_inverted_index.We | 115, 147 |
| abstract_inverted_index.as | 60 |
| abstract_inverted_index.be | 105 |
| abstract_inverted_index.by | 19 |
| abstract_inverted_index.in | 6, 16, 86 |
| abstract_inverted_index.is | 23 |
| abstract_inverted_index.it | 160 |
| abstract_inverted_index.of | 55, 78, 122 |
| abstract_inverted_index.on | 119, 150 |
| abstract_inverted_index.or | 50 |
| abstract_inverted_index.to | 64, 98, 138, 165 |
| abstract_inverted_index.we | 44 |
| abstract_inverted_index.Due | 97 |
| abstract_inverted_index.and | 37, 90, 126, 154, 157 |
| abstract_inverted_index.are | 3, 13, 109 |
| abstract_inverted_index.but | 168 |
| abstract_inverted_index.can | 104, 161 |
| abstract_inverted_index.for | 26 |
| abstract_inverted_index.its | 99 |
| abstract_inverted_index.one | 81 |
| abstract_inverted_index.the | 83, 87, 91, 94, 135 |
| abstract_inverted_index.two | 76, 117 |
| abstract_inverted_index.use | 116 |
| abstract_inverted_index.acts | 59 |
| abstract_inverted_index.from | 107, 111 |
| abstract_inverted_index.less | 171 |
| abstract_inverted_index.much | 143 |
| abstract_inverted_index.show | 158 |
| abstract_inverted_index.that | 58, 132, 159 |
| abstract_inverted_index.this | 42 |
| abstract_inverted_index.type | 121 |
| abstract_inverted_index.used | 15 |
| abstract_inverted_index.with | 28, 69, 142, 169 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.These | 11 |
| abstract_inverted_index.cloud | 39 |
| abstract_inverted_index.data, | 30 |
| abstract_inverted_index.e.g., | 31 |
| abstract_inverted_index.model | 68, 137 |
| abstract_inverted_index.novel | 53 |
| abstract_inverted_index.other | 92 |
| abstract_inverted_index.point | 38 |
| abstract_inverted_index.reach | 162 |
| abstract_inverted_index.small | 34 |
| abstract_inverted_index.tasks | 18, 27 |
| abstract_inverted_index.types | 77 |
| abstract_inverted_index.video | 32 |
| abstract_inverted_index.which | 22, 103 |
| abstract_inverted_index.during | 113 |
| abstract_inverted_index.either | 120 |
| abstract_inverted_index.family | 54 |
| abstract_inverted_index.higher | 144 |
| abstract_inverted_index.highly | 24 |
| abstract_inverted_index.making | 93 |
| abstract_inverted_index.memory | 72, 112, 172 |
| abstract_inverted_index.models | 2, 12, 153 |
| abstract_inverted_index.modern | 7 |
| abstract_inverted_index.object | 35 |
| abstract_inverted_index.paper, | 43 |
| abstract_inverted_index.tasks, | 156 |
| abstract_inverted_index.tasks. | 10 |
| abstract_inverted_index.usage. | 173 |
| abstract_inverted_index.vision | 9 |
| abstract_inverted_index.Dynamic | 46 |
| abstract_inverted_index.cleared | 110 |
| abstract_inverted_index.crucial | 5 |
| abstract_inverted_index.dynamic | 129 |
| abstract_inverted_index.models, | 89 |
| abstract_inverted_index.network | 56, 63, 95, 141 |
| abstract_inverted_index.output, | 108 |
| abstract_inverted_index.propose | 45 |
| abstract_inverted_index.reduced | 71 |
| abstract_inverted_index.various | 151, 155 |
| abstract_inverted_index.computer | 8 |
| abstract_inverted_index.contains | 75 |
| abstract_inverted_index.evaluate | 148 |
| abstract_inverted_index.finetune | 65 |
| abstract_inverted_index.residual | 79, 84, 123 |
| abstract_inverted_index.strategy | 131 |
| abstract_inverted_index.training | 130 |
| abstract_inverted_index.Dr$^2$Net | 74, 149 |
| abstract_inverted_index.Networks, | 49 |
| abstract_inverted_index.analysis. | 40 |
| abstract_inverted_index.introduce | 127 |
| abstract_inverted_index.numerical | 145 |
| abstract_inverted_index.structure | 85 |
| abstract_inverted_index.surrogate | 62 |
| abstract_inverted_index.training. | 114 |
| abstract_inverted_index.typically | 14 |
| abstract_inverted_index.Dr$^2$Net, | 51 |
| abstract_inverted_index.Reversible | 47 |
| abstract_inverted_index.comparable | 163 |
| abstract_inverted_index.detection, | 36 |
| abstract_inverted_index.downstream | 17 |
| abstract_inverted_index.end-to-end | 20 |
| abstract_inverted_index.finetuning | 167 |
| abstract_inverted_index.precision. | 146 |
| abstract_inverted_index.pretrained | 1, 67, 88, 136, 152 |
| abstract_inverted_index.reversible | 140 |
| abstract_inverted_index.seamlessly | 133 |
| abstract_inverted_index.connections | 124 |
| abstract_inverted_index.finetuning, | 21 |
| abstract_inverted_index.maintaining | 82 |
| abstract_inverted_index.performance | 164 |
| abstract_inverted_index.reversible. | 96 |
| abstract_inverted_index.transitions | 134 |
| abstract_inverted_index.activations, | 102 |
| abstract_inverted_index.coefficients | 118 |
| abstract_inverted_index.connections, | 80 |
| abstract_inverted_index.consumption. | 73 |
| abstract_inverted_index.conventional | 166 |
| abstract_inverted_index.increasingly | 4 |
| abstract_inverted_index.intermediate | 101 |
| abstract_inverted_index.Dual-Residual | 48 |
| abstract_inverted_index.architectures | 57 |
| abstract_inverted_index.reconstructed | 106 |
| abstract_inverted_index.respectively, | 125 |
| abstract_inverted_index.significantly | 170 |
| abstract_inverted_index.substantially | 70 |
| abstract_inverted_index.reversibility, | 100 |
| abstract_inverted_index.understanding, | 33 |
| abstract_inverted_index.high-resolution | 29 |
| abstract_inverted_index.memory-intensive | 25 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile.value | 0.51359032 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |