Efficiently Identifying Task Groupings for Multi-Task Learning Article Swipe
Christopher Fifty
,
Ehsan Amid
,
Zhe Zhao
,
Tianhe Yu
,
Rohan Anil
,
Chelsea Finn
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.04617
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.04617
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive. As a result, efficiently identifying the tasks that would benefit from training together remains a challenging design question without a clear solution. In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task groupings in a single run by training all tasks together and quantifying the effect to which one task's gradient would affect another task's loss. On the large-scale Taskonomy computer vision dataset, we find this method can decrease test loss by 10.0% compared to simply training all tasks together while operating 11.6 times faster than a state-of-the-art task grouping method.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2109.04617
- https://arxiv.org/pdf/2109.04617
- OA Status
- green
- Cited By
- 29
- References
- 52
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3200043857
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3200043857Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2109.04617Digital Object Identifier
- Title
-
Efficiently Identifying Task Groupings for Multi-Task LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-09-10Full publication date if available
- Authors
-
Christopher Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu, Rohan Anil, Chelsea FinnList of authors in order
- Landing page
-
https://arxiv.org/abs/2109.04617Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2109.04617Direct 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/2109.04617Direct OA link when available
- Concepts
-
Leverage (statistics), Task (project management), Computer science, Machine learning, Multi-task learning, Artificial intelligence, Task analysis, Engineering, Systems engineeringTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
29Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4, 2024: 12, 2023: 10, 2022: 2, 2021: 1Per-year citation counts (last 5 years)
- References (count)
-
52Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3200043857 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2109.04617 |
| ids.doi | https://doi.org/10.48550/arxiv.2109.04617 |
| ids.mag | 3200043857 |
| ids.openalex | https://openalex.org/W3200043857 |
| fwci | |
| type | preprint |
| title | Efficiently Identifying Task Groupings for Multi-Task Learning |
| biblio.issue | |
| biblio.volume | 34 |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11307 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 1.0 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9997000098228455 |
| 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 Neural Network Applications |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9991999864578247 |
| 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 | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C153083717 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7896745204925537 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q6535263 |
| concepts[0].display_name | Leverage (statistics) |
| concepts[1].id | https://openalex.org/C2780451532 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7492940425872803 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[1].display_name | Task (project management) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.7452164888381958 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5599424839019775 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C28006648 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5341474413871765 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q6934509 |
| concepts[4].display_name | Multi-task learning |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5340650677680969 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C175154964 |
| concepts[6].level | 3 |
| concepts[6].score | 0.41213059425354004 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q380077 |
| concepts[6].display_name | Task analysis |
| concepts[7].id | https://openalex.org/C127413603 |
| concepts[7].level | 0 |
| concepts[7].score | 0.0767856240272522 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[7].display_name | Engineering |
| concepts[8].id | https://openalex.org/C201995342 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[8].display_name | Systems engineering |
| keywords[0].id | https://openalex.org/keywords/leverage |
| keywords[0].score | 0.7896745204925537 |
| keywords[0].display_name | Leverage (statistics) |
| keywords[1].id | https://openalex.org/keywords/task |
| keywords[1].score | 0.7492940425872803 |
| keywords[1].display_name | Task (project management) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.7452164888381958 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.5599424839019775 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/multi-task-learning |
| keywords[4].score | 0.5341474413871765 |
| keywords[4].display_name | Multi-task learning |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5340650677680969 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/task-analysis |
| keywords[6].score | 0.41213059425354004 |
| keywords[6].display_name | Task analysis |
| keywords[7].id | https://openalex.org/keywords/engineering |
| keywords[7].score | 0.0767856240272522 |
| keywords[7].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2109.04617 |
| 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/2109.04617 |
| 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/2109.04617 |
| locations[1].id | mag:3200043857 |
| 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 | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | arXiv (Cornell University) |
| locations[1].landing_page_url | http://arxiv.org/pdf/2109.04617.pdf |
| locations[2].id | doi:10.48550/arxiv.2109.04617 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | article |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.48550/arxiv.2109.04617 |
| locations[3].id | mag:3213501892 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400194 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | arXiv (Cornell University) |
| locations[3].source.host_organization | https://openalex.org/I205783295 |
| locations[3].source.host_organization_name | Cornell University |
| locations[3].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | arXiv (Cornell University) |
| locations[3].landing_page_url | https://arxiv.org/pdf/2109.04617 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5021315343 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Christopher Fifty |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[0].affiliations[0].raw_affiliation_string | Google,,,,, |
| 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 | Christopher Fifty |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Google,,,,, |
| authorships[1].author.id | https://openalex.org/A5056776503 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6097-0226 |
| authorships[1].author.display_name | Ehsan Amid |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[1].affiliations[0].raw_affiliation_string | Google (United States), Mountain View, United States |
| authorships[1].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[1].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Google (United States) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ehsan Amid |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Google (United States), Mountain View, United States |
| authorships[2].author.id | https://openalex.org/A5100631150 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6847-0186 |
| authorships[2].author.display_name | Zhe Zhao |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[2].affiliations[0].raw_affiliation_string | Google (United States), Mountain View, United States |
| 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 | Zhe Zhao |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Google (United States), Mountain View, United States |
| authorships[3].author.id | https://openalex.org/A5100572936 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Tianhe Yu |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I97018004 |
| authorships[3].affiliations[0].raw_affiliation_string | Stanford University, Stanford, United States |
| authorships[3].institutions[0].id | https://openalex.org/I97018004 |
| authorships[3].institutions[0].ror | https://ror.org/00f54p054 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I97018004 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Stanford University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Tianhe Yu |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Stanford University, Stanford, United States |
| authorships[4].author.id | https://openalex.org/A5104083306 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Rohan Anil |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[4].affiliations[0].raw_affiliation_string | Google (United States), Mountain View, United States |
| 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 | Rohan Anil |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Google (United States), Mountain View, United States |
| authorships[5].author.id | https://openalex.org/A5005431772 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-6298-0874 |
| authorships[5].author.display_name | Chelsea Finn |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[5].affiliations[0].raw_affiliation_string | Google (United States), Mountain View, United States |
| 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 | last |
| authorships[5].raw_author_name | Chelsea Finn |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Google (United States), Mountain View, United States |
| 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/2109.04617 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Efficiently Identifying Task Groupings for Multi-Task Learning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11307 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 1.0 |
| 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 | Domain Adaptation and Few-Shot Learning |
| related_works | https://openalex.org/W3094807849, https://openalex.org/W2994972936, https://openalex.org/W2965024236, https://openalex.org/W2993313557, https://openalex.org/W3176879439, https://openalex.org/W2895387432, https://openalex.org/W3200030979, https://openalex.org/W3208451383, https://openalex.org/W1989663016, https://openalex.org/W3164719066, https://openalex.org/W2792402706, https://openalex.org/W2763224350, https://openalex.org/W3129427614, https://openalex.org/W2525330092, https://openalex.org/W2911582157, https://openalex.org/W2056651011, https://openalex.org/W2753445161, https://openalex.org/W2578423033, https://openalex.org/W2944900455, https://openalex.org/W3177878514 |
| cited_by_count | 29 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 12 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 10 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 2 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 1 |
| locations_count | 4 |
| best_oa_location.id | pmh:oai:arXiv.org:2109.04617 |
| 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/2109.04617 |
| 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/2109.04617 |
| primary_location.id | pmh:oai:arXiv.org:2109.04617 |
| 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/2109.04617 |
| 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/2109.04617 |
| publication_date | 2021-09-10 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2964121937, https://openalex.org/W2890538051, https://openalex.org/W2970803838, https://openalex.org/W2996490626, https://openalex.org/W2036043322, https://openalex.org/W2964185501, https://openalex.org/W2884886306, https://openalex.org/W2624871570, https://openalex.org/W2107438106, https://openalex.org/W2895387432, https://openalex.org/W3104240813, https://openalex.org/W3105787868, https://openalex.org/W2549401308, https://openalex.org/W2913340405, https://openalex.org/W2963173418, https://openalex.org/W2997359900, https://openalex.org/W3154938165, https://openalex.org/W2927589347, https://openalex.org/W3101155878, https://openalex.org/W2432541215, https://openalex.org/W1614862348, https://openalex.org/W2251324968, https://openalex.org/W2186054958, https://openalex.org/W2963877604, https://openalex.org/W2994972936, https://openalex.org/W3129958428, https://openalex.org/W2512971201, https://openalex.org/W2931142868, https://openalex.org/W1834627138, https://openalex.org/W2604763608, https://openalex.org/W2949201716, https://openalex.org/W2963821229, https://openalex.org/W2963936326, https://openalex.org/W2996489182, https://openalex.org/W2982303846, https://openalex.org/W2194775991, https://openalex.org/W2975638653, https://openalex.org/W2962743139, https://openalex.org/W2795900505, https://openalex.org/W2970470314, https://openalex.org/W2784596339, https://openalex.org/W2962764337, https://openalex.org/W2963677766, https://openalex.org/W2742079690, https://openalex.org/W1525859397, https://openalex.org/W2946233749, https://openalex.org/W2463008967, https://openalex.org/W2065180801, https://openalex.org/W3033503043, https://openalex.org/W2963430933, https://openalex.org/W3128413221, https://openalex.org/W2991420892 |
| referenced_works_count | 52 |
| abstract_inverted_index.a | 43, 56, 61, 88, 140 |
| abstract_inverted_index.As | 42 |
| abstract_inverted_index.In | 64 |
| abstract_inverted_index.On | 110 |
| abstract_inverted_index.an | 69 |
| abstract_inverted_index.be | 39 |
| abstract_inverted_index.by | 6, 91, 125 |
| abstract_inverted_index.in | 24, 78, 87 |
| abstract_inverted_index.of | 13, 35 |
| abstract_inverted_index.to | 9, 71, 100, 128 |
| abstract_inverted_index.we | 67, 117 |
| abstract_inverted_index.Our | 82 |
| abstract_inverted_index.all | 21, 93, 131 |
| abstract_inverted_index.and | 30, 96 |
| abstract_inverted_index.can | 2, 38, 121 |
| abstract_inverted_index.one | 7, 25, 102 |
| abstract_inverted_index.run | 90 |
| abstract_inverted_index.the | 11, 47, 98, 111 |
| abstract_inverted_index.11.6 | 136 |
| abstract_inverted_index.find | 118 |
| abstract_inverted_index.from | 52 |
| abstract_inverted_index.loss | 124 |
| abstract_inverted_index.task | 8, 36, 85, 142 |
| abstract_inverted_index.test | 123 |
| abstract_inverted_index.than | 139 |
| abstract_inverted_index.that | 49 |
| abstract_inverted_index.this | 17, 65, 119 |
| abstract_inverted_index.10.0% | 126 |
| abstract_inverted_index.clear | 62 |
| abstract_inverted_index.loss. | 109 |
| abstract_inverted_index.model | 26 |
| abstract_inverted_index.often | 27 |
| abstract_inverted_index.other | 14 |
| abstract_inverted_index.tasks | 22, 48, 74, 94, 132 |
| abstract_inverted_index.times | 137 |
| abstract_inverted_index.train | 76 |
| abstract_inverted_index.which | 73, 101 |
| abstract_inverted_index.while | 134 |
| abstract_inverted_index.would | 50, 105 |
| abstract_inverted_index.affect | 106 |
| abstract_inverted_index.design | 58 |
| abstract_inverted_index.effect | 99 |
| abstract_inverted_index.faster | 138 |
| abstract_inverted_index.method | 83, 120 |
| abstract_inverted_index.paper, | 66 |
| abstract_inverted_index.select | 72 |
| abstract_inverted_index.should | 75 |
| abstract_inverted_index.simply | 129 |
| abstract_inverted_index.single | 89 |
| abstract_inverted_index.task's | 103, 108 |
| abstract_inverted_index.tasks. | 15 |
| abstract_inverted_index.vision | 115 |
| abstract_inverted_index.Despite | 16 |
| abstract_inverted_index.another | 107 |
| abstract_inverted_index.benefit | 10, 51 |
| abstract_inverted_index.learned | 5 |
| abstract_inverted_index.method. | 144 |
| abstract_inverted_index.models. | 81 |
| abstract_inverted_index.naively | 19 |
| abstract_inverted_index.remains | 55 |
| abstract_inverted_index.result, | 44 |
| abstract_inverted_index.suggest | 68 |
| abstract_inverted_index.through | 33 |
| abstract_inverted_index.without | 60 |
| abstract_inverted_index.approach | 70 |
| abstract_inverted_index.compared | 127 |
| abstract_inverted_index.computer | 114 |
| abstract_inverted_index.dataset, | 116 |
| abstract_inverted_index.decrease | 122 |
| abstract_inverted_index.degrades | 28 |
| abstract_inverted_index.gradient | 104 |
| abstract_inverted_index.grouping | 143 |
| abstract_inverted_index.learning | 1, 80 |
| abstract_inverted_index.leverage | 3 |
| abstract_inverted_index.question | 59 |
| abstract_inverted_index.together | 23, 54, 77, 95, 133 |
| abstract_inverted_index.training | 12, 20, 53, 92, 130 |
| abstract_inverted_index.Taskonomy | 113 |
| abstract_inverted_index.capacity, | 18 |
| abstract_inverted_index.groupings | 37, 86 |
| abstract_inverted_index.operating | 135 |
| abstract_inverted_index.searching | 32 |
| abstract_inverted_index.solution. | 63 |
| abstract_inverted_index.Multi-task | 0 |
| abstract_inverted_index.determines | 84 |
| abstract_inverted_index.expensive. | 41 |
| abstract_inverted_index.multi-task | 79 |
| abstract_inverted_index.challenging | 57 |
| abstract_inverted_index.efficiently | 45 |
| abstract_inverted_index.identifying | 46 |
| abstract_inverted_index.information | 4 |
| abstract_inverted_index.large-scale | 112 |
| abstract_inverted_index.quantifying | 97 |
| abstract_inverted_index.combinations | 34 |
| abstract_inverted_index.exhaustively | 31 |
| abstract_inverted_index.performance, | 29 |
| abstract_inverted_index.prohibitively | 40 |
| abstract_inverted_index.state-of-the-art | 141 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |