Matryoshka Model Learning for Improved Elastic Student Models Article Swipe
Chetan Verma
,
Aditya Srinivas Timmaraju
,
Cho‐Jui Hsieh
,
Suyash Damle
,
Ngot Bui
,
Yang Zhang
,
Wen Chen
,
Xin Liu
,
Prateek Jain
,
Inderjit S. Dhillon
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1145/3711896.3737245
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1145/3711896.3737245
Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose MatTA, a framework for training multiple accurate Student models using a novel Teacher-TA-Student recipe. TA models are larger versions of the Student models with higher capacity, and thus allow Student models to better relate to the Teacher model and also bring in more domain-specific expertise. Furthermore, multiple accurate Student models can be extracted from the TA model. Therefore, despite only one training run, our methodology provides multiple servable options to trade off accuracy for lower serving cost. We demonstrate the proposed method, MatTA, on proprietary datasets and models. Its practical efficacy is underscored by live A/B tests within a production ML system, demonstrating 20% improvement on a key metric. We also demonstrate our method on GPT-2 Medium, a public model, and achieve relative improvements of over 24% on SAT Math and over 10% on the LAMBADA benchmark.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1145/3711896.3737245
- OA Status
- gold
- References
- 25
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4412876899
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4412876899Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1145/3711896.3737245Digital Object Identifier
- Title
-
Matryoshka Model Learning for Improved Elastic Student ModelsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-08-03Full publication date if available
- Authors
-
Chetan Verma, Aditya Srinivas Timmaraju, Cho‐Jui Hsieh, Suyash Damle, Ngot Bui, Yang Zhang, Wen Chen, Xin Liu, Prateek Jain, Inderjit S. DhillonList of authors in order
- Landing page
-
https://doi.org/10.1145/3711896.3737245Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1145/3711896.3737245Direct OA link when available
- Concepts
-
Computer science, Artificial intelligenceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
25Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4412876899 |
|---|---|
| doi | https://doi.org/10.1145/3711896.3737245 |
| ids.doi | https://doi.org/10.1145/3711896.3737245 |
| ids.openalex | https://openalex.org/W4412876899 |
| fwci | 0.0 |
| type | article |
| title | Matryoshka Model Learning for Improved Elastic Student Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 4944 |
| biblio.first_page | 4935 |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9932000041007996 |
| 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 | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T12282 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9718000292778015 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2210 |
| topics[1].subfield.display_name | Mechanical Engineering |
| topics[1].display_name | Mineral Processing and Grinding |
| topics[2].id | https://openalex.org/T14470 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9577000141143799 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2207 |
| topics[2].subfield.display_name | Control and Systems Engineering |
| topics[2].display_name | Advanced Data Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6754270195960999 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.34177836775779724 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6754270195960999 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.34177836775779724 |
| keywords[1].display_name | Artificial intelligence |
| language | en |
| locations[0].id | doi:10.1145/3711896.3737245 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 |
| locations[0].landing_page_url | https://doi.org/10.1145/3711896.3737245 |
| locations[1].id | pmh:oai:arXiv.org:2505.23337 |
| 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 | https://arxiv.org/pdf/2505.23337 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | text |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2505.23337 |
| indexed_in | arxiv, crossref |
| authorships[0].author.id | https://openalex.org/A5108367698 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4308-2862 |
| authorships[0].author.display_name | Chetan Verma |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[0].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[0].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[0].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Google (United States) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chetan Verma |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[1].author.id | https://openalex.org/A5038137229 |
| authorships[1].author.orcid | https://orcid.org/0009-0001-5934-6079 |
| authorships[1].author.display_name | Aditya Srinivas Timmaraju |
| authorships[1].affiliations[0].raw_affiliation_string | Google DeepMind, Bengaluru, KA, India |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Aditya Srinivas Timmaraju |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Google DeepMind, Bengaluru, KA, India |
| authorships[2].author.id | https://openalex.org/A5010841999 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3520-9627 |
| authorships[2].author.display_name | Cho‐Jui Hsieh |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[2].affiliations[0].raw_affiliation_string | Google, Los Angeles, CA, USA |
| authorships[2].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[2].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | Google (United States) |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Cho-Jui Hsieh |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Google, Los Angeles, CA, USA |
| authorships[3].author.id | https://openalex.org/A5075000586 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6694-0255 |
| authorships[3].author.display_name | Suyash Damle |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[3].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[3].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[3].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[3].institutions[0].type | company |
| authorships[3].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Google (United States) |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Suyash Damle |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[4].author.id | https://openalex.org/A5004306097 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4566-4890 |
| authorships[4].author.display_name | Ngot Bui |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[4].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[4].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[4].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[4].institutions[0].type | company |
| authorships[4].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | Google (United States) |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ngot Bui |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[5].author.id | https://openalex.org/A5101321434 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Yang Zhang |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[5].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[5].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[5].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[5].institutions[0].type | company |
| authorships[5].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[5].institutions[0].country_code | US |
| authorships[5].institutions[0].display_name | Google (United States) |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Yang Zhang |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[6].author.id | https://openalex.org/A5108684531 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Wen Chen |
| authorships[6].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[6].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[6].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[6].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[6].institutions[0].type | company |
| authorships[6].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | Google (United States) |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Wen Chen |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[7].author.id | https://openalex.org/A5077965912 |
| authorships[7].author.orcid | https://orcid.org/0009-0005-9804-7206 |
| authorships[7].author.display_name | Xin Liu |
| authorships[7].countries | US |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[7].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[7].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[7].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[7].institutions[0].type | company |
| authorships[7].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[7].institutions[0].country_code | US |
| authorships[7].institutions[0].display_name | Google (United States) |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Xin Liu |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | Google, Mountain View, CA, USA |
| authorships[8].author.id | https://openalex.org/A5054888556 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-0833-3438 |
| authorships[8].author.display_name | Prateek Jain |
| authorships[8].affiliations[0].raw_affiliation_string | Google DeepMind, Bengaluru, KA, India |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Prateek Jain |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Google DeepMind, Bengaluru, KA, India |
| authorships[9].author.id | https://openalex.org/A5063459703 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-2759-1416 |
| authorships[9].author.display_name | Inderjit S. Dhillon |
| authorships[9].countries | US |
| authorships[9].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[9].affiliations[0].raw_affiliation_string | Google, Mountain View, CA, USA |
| authorships[9].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[9].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[9].institutions[0].type | company |
| authorships[9].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[9].institutions[0].country_code | US |
| authorships[9].institutions[0].display_name | Google (United States) |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Inderjit Dhillon |
| authorships[9].is_corresponding | False |
| authorships[9].raw_affiliation_strings | Google, Mountain View, CA, USA |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1145/3711896.3737245 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Matryoshka Model Learning for Improved Elastic Student Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9932000041007996 |
| 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 | Neural Networks and Applications |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1145/3711896.3737245 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 |
| best_oa_location.landing_page_url | https://doi.org/10.1145/3711896.3737245 |
| primary_location.id | doi:10.1145/3711896.3737245 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 |
| primary_location.landing_page_url | https://doi.org/10.1145/3711896.3737245 |
| publication_date | 2025-08-03 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W3030163527, https://openalex.org/W2146502635, https://openalex.org/W3119866685, https://openalex.org/W6605755289, https://openalex.org/W3096518646, https://openalex.org/W4387848745, https://openalex.org/W2972448360, https://openalex.org/W2512865187, https://openalex.org/W3035588407, https://openalex.org/W2963015836, https://openalex.org/W4402727896, https://openalex.org/W2981852735, https://openalex.org/W2962677625, https://openalex.org/W4387687972, https://openalex.org/W3034896171, https://openalex.org/W2946609015, https://openalex.org/W2987861506, https://openalex.org/W2620998106, https://openalex.org/W4292779060, https://openalex.org/W2990138404, https://openalex.org/W4288089799, https://openalex.org/W3104492324, https://openalex.org/W2750779823, https://openalex.org/W2612690371, https://openalex.org/W4287391717 |
| referenced_works_count | 25 |
| abstract_inverted_index.a | 25, 34, 122, 130, 141 |
| abstract_inverted_index.In | 19 |
| abstract_inverted_index.ML | 1, 124 |
| abstract_inverted_index.TA | 38, 79 |
| abstract_inverted_index.We | 101, 133 |
| abstract_inverted_index.be | 75 |
| abstract_inverted_index.by | 117 |
| abstract_inverted_index.in | 65 |
| abstract_inverted_index.is | 115 |
| abstract_inverted_index.of | 43, 148 |
| abstract_inverted_index.on | 107, 129, 138, 151, 157 |
| abstract_inverted_index.to | 6, 55, 58, 93 |
| abstract_inverted_index.we | 22 |
| abstract_inverted_index.10% | 156 |
| abstract_inverted_index.20% | 127 |
| abstract_inverted_index.24% | 150 |
| abstract_inverted_index.A/B | 119 |
| abstract_inverted_index.Its | 112 |
| abstract_inverted_index.SAT | 152 |
| abstract_inverted_index.and | 50, 62, 110, 144, 154 |
| abstract_inverted_index.are | 3, 40 |
| abstract_inverted_index.can | 74 |
| abstract_inverted_index.for | 16, 27, 97 |
| abstract_inverted_index.key | 131 |
| abstract_inverted_index.off | 95 |
| abstract_inverted_index.one | 84 |
| abstract_inverted_index.our | 87, 136 |
| abstract_inverted_index.the | 44, 59, 78, 103, 158 |
| abstract_inverted_index.Math | 153 |
| abstract_inverted_index.also | 63, 134 |
| abstract_inverted_index.from | 77 |
| abstract_inverted_index.live | 118 |
| abstract_inverted_index.meet | 7 |
| abstract_inverted_index.more | 66 |
| abstract_inverted_index.only | 83 |
| abstract_inverted_index.over | 149, 155 |
| abstract_inverted_index.run, | 86 |
| abstract_inverted_index.this | 20 |
| abstract_inverted_index.thus | 51 |
| abstract_inverted_index.with | 47 |
| abstract_inverted_index.GPT-2 | 139 |
| abstract_inverted_index.allow | 52 |
| abstract_inverted_index.bring | 64 |
| abstract_inverted_index.cost. | 100 |
| abstract_inverted_index.lower | 98 |
| abstract_inverted_index.model | 17, 61 |
| abstract_inverted_index.novel | 35 |
| abstract_inverted_index.tests | 120 |
| abstract_inverted_index.trade | 94 |
| abstract_inverted_index.using | 33 |
| abstract_inverted_index.which | 12 |
| abstract_inverted_index.MatTA, | 24, 106 |
| abstract_inverted_index.better | 56 |
| abstract_inverted_index.higher | 48 |
| abstract_inverted_index.larger | 41 |
| abstract_inverted_index.method | 137 |
| abstract_inverted_index.model, | 143 |
| abstract_inverted_index.model. | 80 |
| abstract_inverted_index.models | 2, 32, 39, 46, 54, 73 |
| abstract_inverted_index.paper, | 21 |
| abstract_inverted_index.public | 142 |
| abstract_inverted_index.relate | 57 |
| abstract_inverted_index.within | 121 |
| abstract_inverted_index.LAMBADA | 159 |
| abstract_inverted_index.Medium, | 140 |
| abstract_inverted_index.Student | 31, 45, 53, 72 |
| abstract_inverted_index.Teacher | 60 |
| abstract_inverted_index.achieve | 145 |
| abstract_inverted_index.despite | 82 |
| abstract_inverted_index.method, | 105 |
| abstract_inverted_index.metric. | 132 |
| abstract_inverted_index.models. | 111 |
| abstract_inverted_index.options | 92 |
| abstract_inverted_index.propose | 23 |
| abstract_inverted_index.rapidly | 8 |
| abstract_inverted_index.recipe. | 37 |
| abstract_inverted_index.serving | 10, 99 |
| abstract_inverted_index.system, | 125 |
| abstract_inverted_index.accuracy | 96 |
| abstract_inverted_index.accurate | 30, 71 |
| abstract_inverted_index.datasets | 109 |
| abstract_inverted_index.designed | 5 |
| abstract_inverted_index.efficacy | 114 |
| abstract_inverted_index.evolving | 9 |
| abstract_inverted_index.multiple | 29, 70, 90 |
| abstract_inverted_index.proposed | 104 |
| abstract_inverted_index.provides | 89 |
| abstract_inverted_index.relative | 146 |
| abstract_inverted_index.requires | 13 |
| abstract_inverted_index.servable | 91 |
| abstract_inverted_index.training | 28, 85 |
| abstract_inverted_index.versions | 42 |
| abstract_inverted_index.capacity, | 49 |
| abstract_inverted_index.carefully | 4 |
| abstract_inverted_index.extracted | 76 |
| abstract_inverted_index.framework | 26 |
| abstract_inverted_index.practical | 113 |
| abstract_inverted_index.resources | 15 |
| abstract_inverted_index.Therefore, | 81 |
| abstract_inverted_index.benchmark. | 160 |
| abstract_inverted_index.expertise. | 68 |
| abstract_inverted_index.production | 123 |
| abstract_inverted_index.demonstrate | 102, 135 |
| abstract_inverted_index.improvement | 128 |
| abstract_inverted_index.methodology | 88 |
| abstract_inverted_index.proprietary | 108 |
| abstract_inverted_index.significant | 14 |
| abstract_inverted_index.underscored | 116 |
| abstract_inverted_index.Furthermore, | 69 |
| abstract_inverted_index.constraints, | 11 |
| abstract_inverted_index.development. | 18 |
| abstract_inverted_index.improvements | 147 |
| abstract_inverted_index.demonstrating | 126 |
| abstract_inverted_index.Industry-grade | 0 |
| abstract_inverted_index.domain-specific | 67 |
| abstract_inverted_index.Teacher-TA-Student | 36 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile.value | 0.14108507 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |