Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention Article Swipe
Xiangcheng Liu
,
Tianyi Wu
,
Guodong Guo
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.24963/ijcai.2023/136
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.24963/ijcai.2023/136
Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts that the complexity is quadratic with respect to the token number, and many tokens containing only background regions do not truly contribute to the final prediction. Existing works either rely on additional modules to score the importance of individual tokens, or implement a fixed ratio pruning strategy for different input instances. In this work, we propose an adaptive sparse token pruning framework with a minimal cost. Specifically, we firstly propose an inexpensive attention head importance weighted class attention scoring mechanism. Then, learnable parameters are inserted as thresholds to distinguish informative tokens from unimportant ones. By comparing token attention scores and thresholds, we can discard useless tokens hierarchically and thus accelerate inference. The learnable thresholds are optimized in budget-aware training to balance accuracy and complexity, performing the corresponding pruning configurations for different input instances. Extensive experiments demonstrate the effectiveness of our approach. Our method improves the throughput of DeiT-S by 50% and brings only 0.2% drop in top-1 accuracy, which achieves a better trade-off between accuracy and latency than the previous methods.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.24963/ijcai.2023/136
- https://www.ijcai.org/proceedings/2023/0136.pdf
- OA Status
- gold
- Cited By
- 15
- References
- 54
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4385768233
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4385768233Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.24963/ijcai.2023/136Digital Object Identifier
- Title
-
Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-AttentionWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-08-01Full publication date if available
- Authors
-
Xiangcheng Liu, Tianyi Wu, Guodong GuoList of authors in order
- Landing page
-
https://doi.org/10.24963/ijcai.2023/136Publisher landing page
- PDF URL
-
https://www.ijcai.org/proceedings/2023/0136.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.ijcai.org/proceedings/2023/0136.pdfDirect OA link when available
- Concepts
-
Security token, Computer science, Pruning, Latency (audio), Inference, Token passing, Artificial intelligence, Quantization (signal processing), Machine learning, Algorithm, Computer security, Biology, Agronomy, TelecommunicationsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
15Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 5, 2024: 7, 2023: 3Per-year citation counts (last 5 years)
- References (count)
-
54Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4385768233 |
|---|---|
| doi | https://doi.org/10.24963/ijcai.2023/136 |
| ids.doi | https://doi.org/10.24963/ijcai.2023/136 |
| ids.openalex | https://openalex.org/W4385768233 |
| fwci | 2.7295251 |
| type | article |
| title | Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 1230 |
| biblio.first_page | 1222 |
| 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 | 0.9997000098228455 |
| 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/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9995999932289124 |
| 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 | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T10775 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9994000196456909 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Generative Adversarial Networks and Image Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C48145219 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8183268308639526 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[0].display_name | Security token |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8161579370498657 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C108010975 |
| concepts[2].level | 2 |
| concepts[2].score | 0.625918984413147 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[2].display_name | Pruning |
| concepts[3].id | https://openalex.org/C82876162 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5175444483757019 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q17096504 |
| concepts[3].display_name | Latency (audio) |
| concepts[4].id | https://openalex.org/C2776214188 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4936271905899048 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[4].display_name | Inference |
| concepts[5].id | https://openalex.org/C115067241 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4802730083465576 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1639854 |
| concepts[5].display_name | Token passing |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.46891507506370544 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C28855332 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4324069619178772 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q198099 |
| concepts[7].display_name | Quantization (signal processing) |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.37560537457466125 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C11413529 |
| concepts[9].level | 1 |
| concepts[9].score | 0.2631024718284607 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[9].display_name | Algorithm |
| concepts[10].id | https://openalex.org/C38652104 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[10].display_name | Computer security |
| concepts[11].id | https://openalex.org/C86803240 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[11].display_name | Biology |
| concepts[12].id | https://openalex.org/C6557445 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[12].display_name | Agronomy |
| concepts[13].id | https://openalex.org/C76155785 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q418 |
| concepts[13].display_name | Telecommunications |
| keywords[0].id | https://openalex.org/keywords/security-token |
| keywords[0].score | 0.8183268308639526 |
| keywords[0].display_name | Security token |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8161579370498657 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/pruning |
| keywords[2].score | 0.625918984413147 |
| keywords[2].display_name | Pruning |
| keywords[3].id | https://openalex.org/keywords/latency |
| keywords[3].score | 0.5175444483757019 |
| keywords[3].display_name | Latency (audio) |
| keywords[4].id | https://openalex.org/keywords/inference |
| keywords[4].score | 0.4936271905899048 |
| keywords[4].display_name | Inference |
| keywords[5].id | https://openalex.org/keywords/token-passing |
| keywords[5].score | 0.4802730083465576 |
| keywords[5].display_name | Token passing |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.46891507506370544 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/quantization |
| keywords[7].score | 0.4324069619178772 |
| keywords[7].display_name | Quantization (signal processing) |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.37560537457466125 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/algorithm |
| keywords[9].score | 0.2631024718284607 |
| keywords[9].display_name | Algorithm |
| language | en |
| locations[0].id | doi:10.24963/ijcai.2023/136 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | https://www.ijcai.org/proceedings/2023/0136.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence |
| locations[0].landing_page_url | https://doi.org/10.24963/ijcai.2023/136 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5046198377 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4966-7394 |
| authorships[0].author.display_name | Xiangcheng Liu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I20231570 |
| authorships[0].affiliations[0].raw_affiliation_string | Peking University |
| authorships[0].institutions[0].id | https://openalex.org/I20231570 |
| authorships[0].institutions[0].ror | https://ror.org/02v51f717 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I20231570 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Peking University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xiangcheng Liu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Peking University |
| authorships[1].author.id | https://openalex.org/A5101956448 |
| authorships[1].author.orcid | https://orcid.org/0009-0004-2308-9965 |
| authorships[1].author.display_name | Tianyi Wu |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[1].affiliations[0].raw_affiliation_string | Baidu Autonomous Driving Technology Department (ADT) |
| authorships[1].institutions[0].id | https://openalex.org/I98301712 |
| authorships[1].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Baidu (China) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Tianyi Wu |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Baidu Autonomous Driving Technology Department (ADT) |
| authorships[2].author.id | https://openalex.org/A5085022758 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9583-0055 |
| authorships[2].author.display_name | Guodong Guo |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[2].affiliations[0].raw_affiliation_string | Institute of Deep Learning, Baidu Research |
| authorships[2].institutions[0].id | https://openalex.org/I98301712 |
| authorships[2].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Baidu (China) |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Guodong Guo |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Institute of Deep Learning, Baidu Research |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.ijcai.org/proceedings/2023/0136.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9997000098228455 |
| 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/W2765256135, https://openalex.org/W2074350650, https://openalex.org/W2540135243, https://openalex.org/W2016681143, https://openalex.org/W2348435129, https://openalex.org/W2013402399, https://openalex.org/W2397526281, https://openalex.org/W2057608425, https://openalex.org/W2136545404, https://openalex.org/W2106477326 |
| cited_by_count | 15 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 7 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 3 |
| locations_count | 1 |
| best_oa_location.id | doi:10.24963/ijcai.2023/136 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://www.ijcai.org/proceedings/2023/0136.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence |
| best_oa_location.landing_page_url | https://doi.org/10.24963/ijcai.2023/136 |
| primary_location.id | doi:10.24963/ijcai.2023/136 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | https://www.ijcai.org/proceedings/2023/0136.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence |
| primary_location.landing_page_url | https://doi.org/10.24963/ijcai.2023/136 |
| publication_date | 2023-08-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W3030520226, https://openalex.org/W6863994431, https://openalex.org/W3169769781, https://openalex.org/W3157528469, https://openalex.org/W2108598243, https://openalex.org/W3094502228, https://openalex.org/W6751979845, https://openalex.org/W3034742519, https://openalex.org/W2194775991, https://openalex.org/W6790825729, https://openalex.org/W6803771590, https://openalex.org/W2748428003, https://openalex.org/W3138516171, https://openalex.org/W2737100304, https://openalex.org/W3174402370, https://openalex.org/W3168124404, https://openalex.org/W2946948417, https://openalex.org/W6864014924, https://openalex.org/W3131500599, https://openalex.org/W6863631769, https://openalex.org/W3139773203, https://openalex.org/W6847742374, https://openalex.org/W3152694111, https://openalex.org/W3188427387, https://openalex.org/W3121523901, https://openalex.org/W6868564194, https://openalex.org/W3194959296, https://openalex.org/W4297813615, https://openalex.org/W4214493665, https://openalex.org/W4308783855, https://openalex.org/W3211490618, https://openalex.org/W2707890836, https://openalex.org/W3122239467, https://openalex.org/W4225365588, https://openalex.org/W4309386164, https://openalex.org/W4308536459, https://openalex.org/W2805003733, https://openalex.org/W2962965870, https://openalex.org/W3096609285, https://openalex.org/W3170874841, https://openalex.org/W3205764742, https://openalex.org/W2808168148, https://openalex.org/W4385245566, https://openalex.org/W4287901267, https://openalex.org/W4239072543, https://openalex.org/W4226484461, https://openalex.org/W4214709605, https://openalex.org/W4376983087, https://openalex.org/W3172801447, https://openalex.org/W2962851801, https://openalex.org/W2964233199, https://openalex.org/W2955425717, https://openalex.org/W4312340826, https://openalex.org/W4287324101 |
| referenced_works_count | 54 |
| abstract_inverted_index.a | 5, 78, 99, 196 |
| abstract_inverted_index.By | 130 |
| abstract_inverted_index.In | 87 |
| abstract_inverted_index.an | 92, 106 |
| abstract_inverted_index.as | 4, 121 |
| abstract_inverted_index.by | 16, 184 |
| abstract_inverted_index.do | 54 |
| abstract_inverted_index.in | 8, 152, 191 |
| abstract_inverted_index.is | 23, 39 |
| abstract_inverted_index.of | 25, 73, 174, 182 |
| abstract_inverted_index.on | 66 |
| abstract_inverted_index.or | 76 |
| abstract_inverted_index.to | 33, 43, 58, 69, 123, 155 |
| abstract_inverted_index.we | 90, 103, 137 |
| abstract_inverted_index.50% | 185 |
| abstract_inverted_index.Our | 177 |
| abstract_inverted_index.The | 147 |
| abstract_inverted_index.ViT | 30 |
| abstract_inverted_index.and | 47, 135, 143, 158, 186, 201 |
| abstract_inverted_index.are | 119, 150 |
| abstract_inverted_index.can | 138 |
| abstract_inverted_index.due | 32 |
| abstract_inverted_index.for | 29, 83, 165 |
| abstract_inverted_index.has | 2 |
| abstract_inverted_index.new | 6 |
| abstract_inverted_index.not | 55 |
| abstract_inverted_index.one | 24 |
| abstract_inverted_index.our | 175 |
| abstract_inverted_index.the | 26, 34, 37, 44, 59, 71, 161, 172, 180, 204 |
| abstract_inverted_index.0.2% | 189 |
| abstract_inverted_index.drop | 190 |
| abstract_inverted_index.from | 127 |
| abstract_inverted_index.head | 109 |
| abstract_inverted_index.main | 27 |
| abstract_inverted_index.many | 48 |
| abstract_inverted_index.only | 51, 188 |
| abstract_inverted_index.rely | 65 |
| abstract_inverted_index.than | 203 |
| abstract_inverted_index.that | 36 |
| abstract_inverted_index.this | 88 |
| abstract_inverted_index.thus | 144 |
| abstract_inverted_index.with | 41, 98 |
| abstract_inverted_index.Image | 20 |
| abstract_inverted_index.Then, | 116 |
| abstract_inverted_index.class | 112 |
| abstract_inverted_index.cost. | 19, 101 |
| abstract_inverted_index.facts | 35 |
| abstract_inverted_index.final | 60 |
| abstract_inverted_index.fixed | 79 |
| abstract_inverted_index.input | 85, 167 |
| abstract_inverted_index.ones. | 129 |
| abstract_inverted_index.ratio | 80 |
| abstract_inverted_index.score | 70 |
| abstract_inverted_index.token | 21, 45, 95, 132 |
| abstract_inverted_index.top-1 | 192 |
| abstract_inverted_index.truly | 56 |
| abstract_inverted_index.which | 194 |
| abstract_inverted_index.while | 14 |
| abstract_inverted_index.work, | 89 |
| abstract_inverted_index.works | 63 |
| abstract_inverted_index.DeiT-S | 183 |
| abstract_inverted_index.Vision | 0 |
| abstract_inverted_index.better | 197 |
| abstract_inverted_index.brings | 187 |
| abstract_inverted_index.either | 64 |
| abstract_inverted_index.method | 178 |
| abstract_inverted_index.scores | 134 |
| abstract_inverted_index.sparse | 94 |
| abstract_inverted_index.tokens | 49, 126, 141 |
| abstract_inverted_index.balance | 156 |
| abstract_inverted_index.between | 199 |
| abstract_inverted_index.discard | 139 |
| abstract_inverted_index.emerged | 3 |
| abstract_inverted_index.firstly | 104 |
| abstract_inverted_index.latency | 202 |
| abstract_inverted_index.minimal | 100 |
| abstract_inverted_index.modules | 68 |
| abstract_inverted_index.number, | 46 |
| abstract_inverted_index.propose | 91, 105 |
| abstract_inverted_index.pruning | 22, 81, 96, 163 |
| abstract_inverted_index.regions | 53 |
| abstract_inverted_index.respect | 42 |
| abstract_inverted_index.scoring | 114 |
| abstract_inverted_index.showing | 11 |
| abstract_inverted_index.tokens, | 75 |
| abstract_inverted_index.useless | 140 |
| abstract_inverted_index.vision, | 10 |
| abstract_inverted_index.Existing | 62 |
| abstract_inverted_index.accuracy | 157, 200 |
| abstract_inverted_index.achieves | 195 |
| abstract_inverted_index.adaptive | 93 |
| abstract_inverted_index.computer | 9 |
| abstract_inverted_index.improves | 179 |
| abstract_inverted_index.inserted | 120 |
| abstract_inverted_index.methods. | 206 |
| abstract_inverted_index.paradigm | 7 |
| abstract_inverted_index.previous | 205 |
| abstract_inverted_index.strategy | 82 |
| abstract_inverted_index.training | 154 |
| abstract_inverted_index.weighted | 111 |
| abstract_inverted_index.Extensive | 169 |
| abstract_inverted_index.accuracy, | 193 |
| abstract_inverted_index.approach. | 176 |
| abstract_inverted_index.attention | 108, 113, 133 |
| abstract_inverted_index.comparing | 131 |
| abstract_inverted_index.different | 84, 166 |
| abstract_inverted_index.excellent | 12 |
| abstract_inverted_index.expensive | 17 |
| abstract_inverted_index.framework | 97 |
| abstract_inverted_index.implement | 77 |
| abstract_inverted_index.learnable | 117, 148 |
| abstract_inverted_index.optimized | 151 |
| abstract_inverted_index.quadratic | 40 |
| abstract_inverted_index.trade-off | 198 |
| abstract_inverted_index.accelerate | 145 |
| abstract_inverted_index.additional | 67 |
| abstract_inverted_index.approaches | 28 |
| abstract_inverted_index.background | 52 |
| abstract_inverted_index.complexity | 38 |
| abstract_inverted_index.containing | 50 |
| abstract_inverted_index.contribute | 57 |
| abstract_inverted_index.importance | 72, 110 |
| abstract_inverted_index.individual | 74 |
| abstract_inverted_index.inference. | 146 |
| abstract_inverted_index.instances. | 86, 168 |
| abstract_inverted_index.mechanism. | 115 |
| abstract_inverted_index.parameters | 118 |
| abstract_inverted_index.performing | 160 |
| abstract_inverted_index.thresholds | 122, 149 |
| abstract_inverted_index.throughput | 181 |
| abstract_inverted_index.accompanied | 15 |
| abstract_inverted_index.complexity, | 159 |
| abstract_inverted_index.demonstrate | 171 |
| abstract_inverted_index.distinguish | 124 |
| abstract_inverted_index.experiments | 170 |
| abstract_inverted_index.inexpensive | 107 |
| abstract_inverted_index.informative | 125 |
| abstract_inverted_index.performance | 13 |
| abstract_inverted_index.prediction. | 61 |
| abstract_inverted_index.thresholds, | 136 |
| abstract_inverted_index.transformer | 1 |
| abstract_inverted_index.unimportant | 128 |
| abstract_inverted_index.budget-aware | 153 |
| abstract_inverted_index.compression, | 31 |
| abstract_inverted_index.Specifically, | 102 |
| abstract_inverted_index.computational | 18 |
| abstract_inverted_index.corresponding | 162 |
| abstract_inverted_index.effectiveness | 173 |
| abstract_inverted_index.configurations | 164 |
| abstract_inverted_index.hierarchically | 142 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 96 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.89703246 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |