Residual Connection Learning by Contextual Modulation Training in Modern Deep Neural Networks Article Swipe
Yingtao Zhang
,
Wanyi Gu
,
Wen-Long Hu
,
Jianguo Li
,
Carlo Vittorio Cannistraci
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.20944/preprints202506.0120.v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.20944/preprints202506.0120.v1
Residual connections are a cornerstone of modern deep neural networks, facilitating stable gradient propagation and maintaining representational expressiveness. Conventional residual formulations typically combine identity mappings and functional transformations with equal weight, without considering the input-dependent importance of each component. This uniformity restricts the model’s capability to adaptively regulate information flow. We propose a novel Contextual Modulation Training (CoMT) framework that introduces lightweight, input-dependent modulation mechanisms to dynamically modulate the functional branches of residual connections. By modulating each transformation based on the incoming data, CoMT enables fine-grained, context-aware control over information flow in the deep learning architecture. This learned modulator provides finer control than prior fixed or hand-designed scaling techniques, improving representational flexibility with a negligible cost on training scalability. CoMT is broadly applicable to architectures that employ residual connections, including ResNets and Transformers. Notably, the modulators are implemented as compact parametric functions, incurring less than 1% of the additional parameters while constantly improving the training performance. Empirical evaluations demonstrate that CoMT achieves 8%–11% perplexity reductions over baseline models across four scales of LLaMA language models, and yields substantial accuracy gains on three scales of ResNet models for image classification tasks. Along with performance improvements, we provide clear evidence that the learned modulators effectively manipulate layer-wise scaling. These findings demonstrate the effectiveness of CoMT as a general mechanism for context-sensitive residual connection modulation.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.20944/preprints202506.0120.v1
- https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pub
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4411014220
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4411014220Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.20944/preprints202506.0120.v1Digital Object Identifier
- Title
-
Residual Connection Learning by Contextual Modulation Training in Modern Deep Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-03Full publication date if available
- Authors
-
Yingtao Zhang, Wanyi Gu, Wen-Long Hu, Jianguo Li, Carlo Vittorio CannistraciList of authors in order
- Landing page
-
https://doi.org/10.20944/preprints202506.0120.v1Publisher landing page
- PDF URL
-
https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pubDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pubDirect OA link when available
- Concepts
-
Residual, Connection (principal bundle), Training (meteorology), Artificial neural network, Computer science, Artificial intelligence, Deep learning, Engineering, Algorithm, Geography, Structural engineering, MeteorologyTop 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/W4411014220 |
|---|---|
| doi | https://doi.org/10.20944/preprints202506.0120.v1 |
| ids.doi | https://doi.org/10.20944/preprints202506.0120.v1 |
| ids.openalex | https://openalex.org/W4411014220 |
| fwci | 0.0 |
| type | preprint |
| title | Residual Connection Learning by Contextual Modulation Training in Modern Deep Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12131 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8752999901771545 |
| 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 | Wireless Signal Modulation Classification |
| 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 | 0.847100019454956 |
| 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 |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C155512373 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7674980163574219 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q287450 |
| concepts[0].display_name | Residual |
| concepts[1].id | https://openalex.org/C13355873 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6611936688423157 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2920850 |
| concepts[1].display_name | Connection (principal bundle) |
| concepts[2].id | https://openalex.org/C2777211547 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6322413682937622 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[2].display_name | Training (meteorology) |
| concepts[3].id | https://openalex.org/C50644808 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5931932330131531 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[3].display_name | Artificial neural network |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.5028218626976013 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4988288879394531 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C108583219 |
| concepts[6].level | 2 |
| concepts[6].score | 0.43016183376312256 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[6].display_name | Deep learning |
| concepts[7].id | https://openalex.org/C127413603 |
| concepts[7].level | 0 |
| concepts[7].score | 0.16859447956085205 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[7].display_name | Engineering |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.09767940640449524 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C205649164 |
| concepts[9].level | 0 |
| concepts[9].score | 0.09147074818611145 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[9].display_name | Geography |
| concepts[10].id | https://openalex.org/C66938386 |
| concepts[10].level | 1 |
| concepts[10].score | 0.056201398372650146 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q633538 |
| concepts[10].display_name | Structural engineering |
| concepts[11].id | https://openalex.org/C153294291 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[11].display_name | Meteorology |
| keywords[0].id | https://openalex.org/keywords/residual |
| keywords[0].score | 0.7674980163574219 |
| keywords[0].display_name | Residual |
| keywords[1].id | https://openalex.org/keywords/connection |
| keywords[1].score | 0.6611936688423157 |
| keywords[1].display_name | Connection (principal bundle) |
| keywords[2].id | https://openalex.org/keywords/training |
| keywords[2].score | 0.6322413682937622 |
| keywords[2].display_name | Training (meteorology) |
| keywords[3].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[3].score | 0.5931932330131531 |
| keywords[3].display_name | Artificial neural network |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.5028218626976013 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.4988288879394531 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/deep-learning |
| keywords[6].score | 0.43016183376312256 |
| keywords[6].display_name | Deep learning |
| keywords[7].id | https://openalex.org/keywords/engineering |
| keywords[7].score | 0.16859447956085205 |
| keywords[7].display_name | Engineering |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.09767940640449524 |
| keywords[8].display_name | Algorithm |
| keywords[9].id | https://openalex.org/keywords/geography |
| keywords[9].score | 0.09147074818611145 |
| keywords[9].display_name | Geography |
| keywords[10].id | https://openalex.org/keywords/structural-engineering |
| keywords[10].score | 0.056201398372650146 |
| keywords[10].display_name | Structural engineering |
| language | en |
| locations[0].id | doi:10.20944/preprints202506.0120.v1 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S6309402219 |
| 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 | Preprints.org |
| locations[0].source.host_organization | |
| locations[0].source.host_organization_name | |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310310987 |
| locations[0].source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pub |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.20944/preprints202506.0120.v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5032429023 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8587-9645 |
| authorships[0].author.display_name | Yingtao Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yingtao Zhang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101829505 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6430-1836 |
| authorships[1].author.display_name | Wanyi Gu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wenqi Gu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5057582269 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9549-6202 |
| authorships[2].author.display_name | Wen-Long Hu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Wen Hu |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100368363 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0282-7891 |
| authorships[3].author.display_name | Jianguo Li |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jianguo Li |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5007730744 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0100-8410 |
| authorships[4].author.display_name | Carlo Vittorio Cannistraci |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Carlo Vittorio Cannistraci |
| authorships[4].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://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pub |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Residual Connection Learning by Contextual Modulation Training in Modern Deep Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12131 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8752999901771545 |
| 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 | Wireless Signal Modulation Classification |
| related_works | https://openalex.org/W587735977, https://openalex.org/W230091440, https://openalex.org/W1978142926, https://openalex.org/W3157395178, https://openalex.org/W2560215812, https://openalex.org/W2233261550, https://openalex.org/W2810751659, https://openalex.org/W258997015, https://openalex.org/W2949601986, https://openalex.org/W2997094352 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.20944/preprints202506.0120.v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S6309402219 |
| 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 | Preprints.org |
| best_oa_location.source.host_organization | |
| best_oa_location.source.host_organization_name | |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| best_oa_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pub |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.20944/preprints202506.0120.v1 |
| primary_location.id | doi:10.20944/preprints202506.0120.v1 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S6309402219 |
| 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 | Preprints.org |
| primary_location.source.host_organization | |
| primary_location.source.host_organization_name | |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310310987 |
| primary_location.source.host_organization_lineage_names | Multidisciplinary Digital Publishing Institute |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.preprints.org/frontend/manuscript/cdf4d41b768ee832f2ad99ee0d95b6ef/download_pub |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.20944/preprints202506.0120.v1 |
| publication_date | 2025-06-03 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 3, 52, 113, 214 |
| abstract_inverted_index.1% | 145 |
| abstract_inverted_index.By | 74 |
| abstract_inverted_index.We | 50 |
| abstract_inverted_index.as | 138, 213 |
| abstract_inverted_index.in | 91 |
| abstract_inverted_index.is | 120 |
| abstract_inverted_index.of | 5, 36, 71, 146, 171, 183, 211 |
| abstract_inverted_index.on | 79, 116, 180 |
| abstract_inverted_index.or | 105 |
| abstract_inverted_index.to | 45, 65, 123 |
| abstract_inverted_index.we | 194 |
| abstract_inverted_index.and | 14, 25, 131, 175 |
| abstract_inverted_index.are | 2, 136 |
| abstract_inverted_index.for | 186, 217 |
| abstract_inverted_index.the | 33, 42, 68, 80, 92, 134, 147, 153, 199, 209 |
| abstract_inverted_index.CoMT | 83, 119, 160, 212 |
| abstract_inverted_index.This | 39, 96 |
| abstract_inverted_index.cost | 115 |
| abstract_inverted_index.deep | 7, 93 |
| abstract_inverted_index.each | 37, 76 |
| abstract_inverted_index.flow | 90 |
| abstract_inverted_index.four | 169 |
| abstract_inverted_index.less | 143 |
| abstract_inverted_index.over | 88, 165 |
| abstract_inverted_index.than | 102, 144 |
| abstract_inverted_index.that | 59, 125, 159, 198 |
| abstract_inverted_index.with | 28, 112, 191 |
| abstract_inverted_index.Along | 190 |
| abstract_inverted_index.LLaMA | 172 |
| abstract_inverted_index.These | 206 |
| abstract_inverted_index.based | 78 |
| abstract_inverted_index.clear | 196 |
| abstract_inverted_index.data, | 82 |
| abstract_inverted_index.equal | 29 |
| abstract_inverted_index.finer | 100 |
| abstract_inverted_index.fixed | 104 |
| abstract_inverted_index.flow. | 49 |
| abstract_inverted_index.gains | 179 |
| abstract_inverted_index.image | 187 |
| abstract_inverted_index.novel | 53 |
| abstract_inverted_index.prior | 103 |
| abstract_inverted_index.three | 181 |
| abstract_inverted_index.while | 150 |
| abstract_inverted_index.(CoMT) | 57 |
| abstract_inverted_index.ResNet | 184 |
| abstract_inverted_index.across | 168 |
| abstract_inverted_index.employ | 126 |
| abstract_inverted_index.models | 167, 185 |
| abstract_inverted_index.modern | 6 |
| abstract_inverted_index.neural | 8 |
| abstract_inverted_index.scales | 170, 182 |
| abstract_inverted_index.stable | 11 |
| abstract_inverted_index.tasks. | 189 |
| abstract_inverted_index.yields | 176 |
| abstract_inverted_index.ResNets | 130 |
| abstract_inverted_index.broadly | 121 |
| abstract_inverted_index.combine | 22 |
| abstract_inverted_index.compact | 139 |
| abstract_inverted_index.control | 87, 101 |
| abstract_inverted_index.enables | 84 |
| abstract_inverted_index.general | 215 |
| abstract_inverted_index.learned | 97, 200 |
| abstract_inverted_index.models, | 174 |
| abstract_inverted_index.propose | 51 |
| abstract_inverted_index.provide | 195 |
| abstract_inverted_index.scaling | 107 |
| abstract_inverted_index.weight, | 30 |
| abstract_inverted_index.without | 31 |
| abstract_inverted_index.8%–11% | 162 |
| abstract_inverted_index.Notably, | 133 |
| abstract_inverted_index.Residual | 0 |
| abstract_inverted_index.Training | 56 |
| abstract_inverted_index.accuracy | 178 |
| abstract_inverted_index.achieves | 161 |
| abstract_inverted_index.baseline | 166 |
| abstract_inverted_index.branches | 70 |
| abstract_inverted_index.evidence | 197 |
| abstract_inverted_index.findings | 207 |
| abstract_inverted_index.gradient | 12 |
| abstract_inverted_index.identity | 23 |
| abstract_inverted_index.incoming | 81 |
| abstract_inverted_index.language | 173 |
| abstract_inverted_index.learning | 94 |
| abstract_inverted_index.mappings | 24 |
| abstract_inverted_index.modulate | 67 |
| abstract_inverted_index.provides | 99 |
| abstract_inverted_index.regulate | 47 |
| abstract_inverted_index.residual | 19, 72, 127, 219 |
| abstract_inverted_index.scaling. | 205 |
| abstract_inverted_index.training | 117, 154 |
| abstract_inverted_index.Empirical | 156 |
| abstract_inverted_index.framework | 58 |
| abstract_inverted_index.improving | 109, 152 |
| abstract_inverted_index.including | 129 |
| abstract_inverted_index.incurring | 142 |
| abstract_inverted_index.mechanism | 216 |
| abstract_inverted_index.model’s | 43 |
| abstract_inverted_index.modulator | 98 |
| abstract_inverted_index.networks, | 9 |
| abstract_inverted_index.restricts | 41 |
| abstract_inverted_index.typically | 21 |
| abstract_inverted_index.Contextual | 54 |
| abstract_inverted_index.Modulation | 55 |
| abstract_inverted_index.adaptively | 46 |
| abstract_inverted_index.additional | 148 |
| abstract_inverted_index.applicable | 122 |
| abstract_inverted_index.capability | 44 |
| abstract_inverted_index.component. | 38 |
| abstract_inverted_index.connection | 220 |
| abstract_inverted_index.constantly | 151 |
| abstract_inverted_index.functional | 26, 69 |
| abstract_inverted_index.functions, | 141 |
| abstract_inverted_index.importance | 35 |
| abstract_inverted_index.introduces | 60 |
| abstract_inverted_index.layer-wise | 204 |
| abstract_inverted_index.manipulate | 203 |
| abstract_inverted_index.mechanisms | 64 |
| abstract_inverted_index.modulating | 75 |
| abstract_inverted_index.modulation | 63 |
| abstract_inverted_index.modulators | 135, 201 |
| abstract_inverted_index.negligible | 114 |
| abstract_inverted_index.parameters | 149 |
| abstract_inverted_index.parametric | 140 |
| abstract_inverted_index.perplexity | 163 |
| abstract_inverted_index.reductions | 164 |
| abstract_inverted_index.uniformity | 40 |
| abstract_inverted_index.connections | 1 |
| abstract_inverted_index.considering | 32 |
| abstract_inverted_index.cornerstone | 4 |
| abstract_inverted_index.demonstrate | 158, 208 |
| abstract_inverted_index.dynamically | 66 |
| abstract_inverted_index.effectively | 202 |
| abstract_inverted_index.evaluations | 157 |
| abstract_inverted_index.flexibility | 111 |
| abstract_inverted_index.implemented | 137 |
| abstract_inverted_index.information | 48, 89 |
| abstract_inverted_index.maintaining | 15 |
| abstract_inverted_index.modulation. | 221 |
| abstract_inverted_index.performance | 192 |
| abstract_inverted_index.propagation | 13 |
| abstract_inverted_index.substantial | 177 |
| abstract_inverted_index.techniques, | 108 |
| abstract_inverted_index.Conventional | 18 |
| abstract_inverted_index.connections, | 128 |
| abstract_inverted_index.connections. | 73 |
| abstract_inverted_index.facilitating | 10 |
| abstract_inverted_index.formulations | 20 |
| abstract_inverted_index.lightweight, | 61 |
| abstract_inverted_index.performance. | 155 |
| abstract_inverted_index.scalability. | 118 |
| abstract_inverted_index.Transformers. | 132 |
| abstract_inverted_index.architecture. | 95 |
| abstract_inverted_index.architectures | 124 |
| abstract_inverted_index.context-aware | 86 |
| abstract_inverted_index.effectiveness | 210 |
| abstract_inverted_index.fine-grained, | 85 |
| abstract_inverted_index.hand-designed | 106 |
| abstract_inverted_index.improvements, | 193 |
| abstract_inverted_index.classification | 188 |
| abstract_inverted_index.transformation | 77 |
| abstract_inverted_index.expressiveness. | 17 |
| abstract_inverted_index.input-dependent | 34, 62 |
| abstract_inverted_index.transformations | 27 |
| abstract_inverted_index.representational | 16, 110 |
| abstract_inverted_index.context-sensitive | 218 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.08807841 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |