Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks Article Swipe
Zixuan Ke
,
Bing Liu
,
Wenhan Xiong
,
Aslı Çelikyılmaz
,
Haoran Li
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.09436
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.09436
Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are similar. To our knowledge, only one method has been proposed to learn a sequence of mixed tasks. However, these techniques still suffer from CF and/or limited KT. This paper proposes a new CL method to achieve both. It overcomes CF by isolating the knowledge of each task via discovering a subnetwork for it. A soft-masking mechanism is also proposed to preserve the previous knowledge and to enable the new task to leverage the past knowledge to achieve KT. Experiments using classification, generation, information extraction, and their mixture (i.e., heterogeneous tasks) show that the proposed method consistently outperforms strong baselines.
Related Topics
Concepts
Forgetting
Computer science
Leverage (statistics)
Subnetwork
Task (project management)
Artificial intelligence
Knowledge transfer
Machine learning
Transfer of learning
Knowledge extraction
Sequence (biology)
Knowledge management
Engineering
Genetics
Linguistics
Biology
Philosophy
Systems engineering
Computer security
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.09436
- https://arxiv.org/pdf/2310.09436
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387723594
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387723594Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.09436Digital Object Identifier
- Title
-
Sub-network Discovery and Soft-masking for Continual Learning of Mixed TasksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-13Full publication date if available
- Authors
-
Zixuan Ke, Bing Liu, Wenhan Xiong, Aslı Çelikyılmaz, Haoran LiList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.09436Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.09436Direct 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/2310.09436Direct OA link when available
- Concepts
-
Forgetting, Computer science, Leverage (statistics), Subnetwork, Task (project management), Artificial intelligence, Knowledge transfer, Machine learning, Transfer of learning, Knowledge extraction, Sequence (biology), Knowledge management, Engineering, Genetics, Linguistics, Biology, Philosophy, Systems engineering, Computer securityTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387723594 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.09436 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.09436 |
| ids.openalex | https://openalex.org/W4387723594 |
| fwci | 0.25544289 |
| type | preprint |
| title | Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks |
| biblio.issue | |
| biblio.volume | |
| 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 | 0.9952999949455261 |
| 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/T11714 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9599999785423279 |
| 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 | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C7149132 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7756167650222778 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1377840 |
| concepts[0].display_name | Forgetting |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.746752142906189 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C153083717 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7221657037734985 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q6535263 |
| concepts[2].display_name | Leverage (statistics) |
| concepts[3].id | https://openalex.org/C2780186347 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5992318391799927 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11414 |
| concepts[3].display_name | Subnetwork |
| concepts[4].id | https://openalex.org/C2780451532 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5510271191596985 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[4].display_name | Task (project management) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4662166237831116 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C2776960227 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4627065658569336 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2586354 |
| concepts[6].display_name | Knowledge transfer |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4599967896938324 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C150899416 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4523719549179077 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q1820378 |
| concepts[8].display_name | Transfer of learning |
| concepts[9].id | https://openalex.org/C120567893 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4365246891975403 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1582085 |
| concepts[9].display_name | Knowledge extraction |
| concepts[10].id | https://openalex.org/C2778112365 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4275874197483063 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q3511065 |
| concepts[10].display_name | Sequence (biology) |
| concepts[11].id | https://openalex.org/C56739046 |
| concepts[11].level | 1 |
| concepts[11].score | 0.15327271819114685 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q192060 |
| concepts[11].display_name | Knowledge management |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.09053435921669006 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C54355233 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7162 |
| concepts[13].display_name | Genetics |
| concepts[14].id | https://openalex.org/C41895202 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[14].display_name | Linguistics |
| concepts[15].id | https://openalex.org/C86803240 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[15].display_name | Biology |
| concepts[16].id | https://openalex.org/C138885662 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[16].display_name | Philosophy |
| concepts[17].id | https://openalex.org/C201995342 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[17].display_name | Systems engineering |
| concepts[18].id | https://openalex.org/C38652104 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[18].display_name | Computer security |
| keywords[0].id | https://openalex.org/keywords/forgetting |
| keywords[0].score | 0.7756167650222778 |
| keywords[0].display_name | Forgetting |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.746752142906189 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/leverage |
| keywords[2].score | 0.7221657037734985 |
| keywords[2].display_name | Leverage (statistics) |
| keywords[3].id | https://openalex.org/keywords/subnetwork |
| keywords[3].score | 0.5992318391799927 |
| keywords[3].display_name | Subnetwork |
| keywords[4].id | https://openalex.org/keywords/task |
| keywords[4].score | 0.5510271191596985 |
| keywords[4].display_name | Task (project management) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.4662166237831116 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/knowledge-transfer |
| keywords[6].score | 0.4627065658569336 |
| keywords[6].display_name | Knowledge transfer |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.4599967896938324 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/transfer-of-learning |
| keywords[8].score | 0.4523719549179077 |
| keywords[8].display_name | Transfer of learning |
| keywords[9].id | https://openalex.org/keywords/knowledge-extraction |
| keywords[9].score | 0.4365246891975403 |
| keywords[9].display_name | Knowledge extraction |
| keywords[10].id | https://openalex.org/keywords/sequence |
| keywords[10].score | 0.4275874197483063 |
| keywords[10].display_name | Sequence (biology) |
| keywords[11].id | https://openalex.org/keywords/knowledge-management |
| keywords[11].score | 0.15327271819114685 |
| keywords[11].display_name | Knowledge management |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.09053435921669006 |
| keywords[12].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.09436 |
| 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/2310.09436 |
| 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/2310.09436 |
| locations[1].id | doi:10.48550/arxiv.2310.09436 |
| 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 | public-domain |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article-journal |
| locations[1].license_id | https://openalex.org/licenses/public-domain |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2310.09436 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5013224749 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zixuan Ke |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ke, Zixuan |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100339921 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2365-6606 |
| authorships[1].author.display_name | Bing Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liu, Bing |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5110635444 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Wenhan Xiong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xiong, Wenhan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5030468199 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Aslı Çelikyılmaz |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Celikyilmaz, Asli |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100327731 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-5641-1058 |
| authorships[4].author.display_name | Haoran Li |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Li, Haoran |
| authorships[4].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2310.09436 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-10-18T00:00:00 |
| display_name | Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks |
| 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 | 0.9952999949455261 |
| 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/W2060724872, https://openalex.org/W2082094785, https://openalex.org/W2202198356, https://openalex.org/W3087203342, https://openalex.org/W2377184161, https://openalex.org/W228984114, https://openalex.org/W2090026684, https://openalex.org/W4226360758, https://openalex.org/W2907567977, https://openalex.org/W3153861134 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.09436 |
| 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/2310.09436 |
| 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/2310.09436 |
| primary_location.id | pmh:oai:arXiv.org:2310.09436 |
| 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/2310.09436 |
| 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/2310.09436 |
| publication_date | 2023-10-13 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.A | 89 |
| abstract_inverted_index.a | 48, 66, 85 |
| abstract_inverted_index.CF | 59, 75 |
| abstract_inverted_index.CL | 68 |
| abstract_inverted_index.It | 73 |
| abstract_inverted_index.KT | 31 |
| abstract_inverted_index.To | 37 |
| abstract_inverted_index.by | 76 |
| abstract_inverted_index.is | 92 |
| abstract_inverted_index.of | 50, 80 |
| abstract_inverted_index.on | 21, 30 |
| abstract_inverted_index.to | 46, 70, 95, 101, 106, 111 |
| abstract_inverted_index.CF. | 23 |
| abstract_inverted_index.KT. | 62, 113 |
| abstract_inverted_index.The | 16 |
| abstract_inverted_index.and | 11, 100, 120 |
| abstract_inverted_index.are | 35 |
| abstract_inverted_index.for | 87 |
| abstract_inverted_index.has | 3, 26, 43 |
| abstract_inverted_index.it. | 88 |
| abstract_inverted_index.new | 67, 104 |
| abstract_inverted_index.one | 41 |
| abstract_inverted_index.our | 38 |
| abstract_inverted_index.the | 33, 78, 97, 103, 108, 128 |
| abstract_inverted_index.two | 4 |
| abstract_inverted_index.via | 83 |
| abstract_inverted_index.(CF) | 10 |
| abstract_inverted_index.(CL) | 2 |
| abstract_inverted_index.Some | 24 |
| abstract_inverted_index.This | 63 |
| abstract_inverted_index.also | 27, 93 |
| abstract_inverted_index.been | 28, 44 |
| abstract_inverted_index.done | 29 |
| abstract_inverted_index.each | 81 |
| abstract_inverted_index.from | 58 |
| abstract_inverted_index.main | 5 |
| abstract_inverted_index.only | 40 |
| abstract_inverted_index.past | 109 |
| abstract_inverted_index.show | 126 |
| abstract_inverted_index.task | 82, 105 |
| abstract_inverted_index.that | 127 |
| abstract_inverted_index.when | 32 |
| abstract_inverted_index.work | 25 |
| abstract_inverted_index.(KT). | 15 |
| abstract_inverted_index.both. | 72 |
| abstract_inverted_index.learn | 47 |
| abstract_inverted_index.mixed | 51 |
| abstract_inverted_index.paper | 64 |
| abstract_inverted_index.still | 56 |
| abstract_inverted_index.tasks | 34 |
| abstract_inverted_index.their | 121 |
| abstract_inverted_index.these | 54 |
| abstract_inverted_index.using | 115 |
| abstract_inverted_index.(i.e., | 123 |
| abstract_inverted_index.and/or | 60 |
| abstract_inverted_index.enable | 102 |
| abstract_inverted_index.mainly | 19 |
| abstract_inverted_index.method | 42, 69, 130 |
| abstract_inverted_index.strong | 133 |
| abstract_inverted_index.suffer | 57 |
| abstract_inverted_index.tasks) | 125 |
| abstract_inverted_index.tasks. | 52 |
| abstract_inverted_index.achieve | 71, 112 |
| abstract_inverted_index.focused | 20 |
| abstract_inverted_index.limited | 61 |
| abstract_inverted_index.mixture | 122 |
| abstract_inverted_index.However, | 53 |
| abstract_inverted_index.existing | 17 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.leverage | 107 |
| abstract_inverted_index.preserve | 96 |
| abstract_inverted_index.previous | 98 |
| abstract_inverted_index.proposed | 45, 94, 129 |
| abstract_inverted_index.proposes | 65 |
| abstract_inverted_index.sequence | 49 |
| abstract_inverted_index.similar. | 36 |
| abstract_inverted_index.transfer | 14 |
| abstract_inverted_index.Continual | 0 |
| abstract_inverted_index.isolating | 77 |
| abstract_inverted_index.knowledge | 13, 79, 99, 110 |
| abstract_inverted_index.mechanism | 91 |
| abstract_inverted_index.overcomes | 74 |
| abstract_inverted_index.baselines. | 134 |
| abstract_inverted_index.forgetting | 9 |
| abstract_inverted_index.knowledge, | 39 |
| abstract_inverted_index.literature | 18 |
| abstract_inverted_index.overcoming | 22 |
| abstract_inverted_index.preventing | 7 |
| abstract_inverted_index.subnetwork | 86 |
| abstract_inverted_index.techniques | 55 |
| abstract_inverted_index.Experiments | 114 |
| abstract_inverted_index.discovering | 84 |
| abstract_inverted_index.encouraging | 12 |
| abstract_inverted_index.extraction, | 119 |
| abstract_inverted_index.generation, | 117 |
| abstract_inverted_index.information | 118 |
| abstract_inverted_index.objectives: | 6 |
| abstract_inverted_index.outperforms | 132 |
| abstract_inverted_index.catastrophic | 8 |
| abstract_inverted_index.consistently | 131 |
| abstract_inverted_index.soft-masking | 90 |
| abstract_inverted_index.heterogeneous | 124 |
| abstract_inverted_index.classification, | 116 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.4699999988079071 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile.value | 0.59148989 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |