Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts Article Swipe
Basil Mustafa
,
Carlos Riquelme
,
Joan Puigcerver
,
Rodolphe Jenatton
,
Neil Houlsby
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2206.02770
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2206.02770
Large sparsely-activated models have obtained excellent performance in multiple domains. However, such models are typically trained on a single modality at a time. We present the Language-Image MoE, LIMoE, a sparse mixture of experts model capable of multimodal learning. LIMoE accepts both images and text simultaneously, while being trained using a contrastive loss. MoEs are a natural fit for a multimodal backbone, since expert layers can learn an appropriate partitioning of modalities. However, new challenges arise; in particular, training stability and balanced expert utilization, for which we propose an entropy-based regularization scheme. Across multiple scales, we demonstrate remarkable performance improvement over dense models of equivalent computational cost. LIMoE-L/16 trained comparably to CLIP-L/14 achieves 78.6% zero-shot ImageNet accuracy (vs. 76.2%), and when further scaled to H/14 (with additional data) it achieves 84.1%, comparable to state-of-the-art methods which use larger custom per-modality backbones and pre-training schemes. We analyse the quantitative and qualitative behavior of LIMoE, and demonstrate phenomena such as differing treatment of the modalities and the organic emergence of modality-specific experts.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2206.02770
- https://arxiv.org/pdf/2206.02770
- OA Status
- green
- Cited By
- 72
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4282028729
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4282028729Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2206.02770Digital Object Identifier
- Title
-
Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of ExpertsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-06-06Full publication date if available
- Authors
-
Basil Mustafa, Carlos Riquelme, Joan Puigcerver, Rodolphe Jenatton, Neil HoulsbyList of authors in order
- Landing page
-
https://arxiv.org/abs/2206.02770Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2206.02770Direct 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/2206.02770Direct OA link when available
- Concepts
-
Computer science, Modalities, Artificial intelligence, Modality (human–computer interaction), Regularization (linguistics), Machine learning, Natural language processing, Image (mathematics), Stability (learning theory), Pattern recognition (psychology), Social science, SociologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
72Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 29, 2024: 19, 2023: 21, 2022: 3Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4282028729 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2206.02770 |
| ids.doi | https://doi.org/10.48550/arxiv.2206.02770 |
| ids.openalex | https://openalex.org/W4282028729 |
| fwci | |
| type | preprint |
| title | Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11714 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9995999932289124 |
| 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 | Multimodal Machine Learning Applications |
| topics[1].id | https://openalex.org/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9948999881744385 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9550999999046326 |
| 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 | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7516770362854004 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2779903281 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6929954886436462 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q6888026 |
| concepts[1].display_name | Modalities |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.6645853519439697 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C2780226545 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5646705627441406 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q6888030 |
| concepts[3].display_name | Modality (human–computer interaction) |
| concepts[4].id | https://openalex.org/C2776135515 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5326851010322571 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[4].display_name | Regularization (linguistics) |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4804060757160187 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C204321447 |
| concepts[6].level | 1 |
| concepts[6].score | 0.4404946565628052 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[6].display_name | Natural language processing |
| concepts[7].id | https://openalex.org/C115961682 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4169095456600189 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[7].display_name | Image (mathematics) |
| concepts[8].id | https://openalex.org/C112972136 |
| concepts[8].level | 2 |
| concepts[8].score | 0.41647934913635254 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7595718 |
| concepts[8].display_name | Stability (learning theory) |
| concepts[9].id | https://openalex.org/C153180895 |
| concepts[9].level | 2 |
| concepts[9].score | 0.377533495426178 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[9].display_name | Pattern recognition (psychology) |
| concepts[10].id | https://openalex.org/C36289849 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q34749 |
| concepts[10].display_name | Social science |
| concepts[11].id | https://openalex.org/C144024400 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[11].display_name | Sociology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7516770362854004 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/modalities |
| keywords[1].score | 0.6929954886436462 |
| keywords[1].display_name | Modalities |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.6645853519439697 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/modality |
| keywords[3].score | 0.5646705627441406 |
| keywords[3].display_name | Modality (human–computer interaction) |
| keywords[4].id | https://openalex.org/keywords/regularization |
| keywords[4].score | 0.5326851010322571 |
| keywords[4].display_name | Regularization (linguistics) |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.4804060757160187 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/natural-language-processing |
| keywords[6].score | 0.4404946565628052 |
| keywords[6].display_name | Natural language processing |
| keywords[7].id | https://openalex.org/keywords/image |
| keywords[7].score | 0.4169095456600189 |
| keywords[7].display_name | Image (mathematics) |
| keywords[8].id | https://openalex.org/keywords/stability |
| keywords[8].score | 0.41647934913635254 |
| keywords[8].display_name | Stability (learning theory) |
| keywords[9].id | https://openalex.org/keywords/pattern-recognition |
| keywords[9].score | 0.377533495426178 |
| keywords[9].display_name | Pattern recognition (psychology) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2206.02770 |
| 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/2206.02770 |
| 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/2206.02770 |
| locations[1].id | doi:10.48550/arxiv.2206.02770 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2206.02770 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5072796087 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7305-7890 |
| authorships[0].author.display_name | Basil Mustafa |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mustafa, Basil |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5112854801 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Carlos Riquelme |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Riquelme, Carlos |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5001091279 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1926-2233 |
| authorships[2].author.display_name | Joan Puigcerver |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Puigcerver, Joan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5033851429 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Rodolphe Jenatton |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jenatton, Rodolphe |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5068878643 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Neil Houlsby |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Houlsby, Neil |
| 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/2206.02770 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-06-13T00:00:00 |
| display_name | Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11714 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9995999932289124 |
| 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 | Multimodal Machine Learning Applications |
| related_works | https://openalex.org/W73545470, https://openalex.org/W4224266612, https://openalex.org/W2383394264, https://openalex.org/W4320153225, https://openalex.org/W4293261942, https://openalex.org/W3125968744, https://openalex.org/W2167701463, https://openalex.org/W2110287964, https://openalex.org/W4307407935, https://openalex.org/W649759291 |
| cited_by_count | 72 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 29 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 19 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 21 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2206.02770 |
| 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/2206.02770 |
| 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/2206.02770 |
| primary_location.id | pmh:oai:arXiv.org:2206.02770 |
| 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/2206.02770 |
| 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/2206.02770 |
| publication_date | 2022-06-06 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 17, 21, 29, 50, 55, 59 |
| abstract_inverted_index.We | 23, 144 |
| abstract_inverted_index.an | 67, 88 |
| abstract_inverted_index.as | 157 |
| abstract_inverted_index.at | 20 |
| abstract_inverted_index.in | 7, 76 |
| abstract_inverted_index.it | 128 |
| abstract_inverted_index.of | 32, 36, 70, 103, 151, 160, 167 |
| abstract_inverted_index.on | 16 |
| abstract_inverted_index.to | 110, 123, 132 |
| abstract_inverted_index.we | 86, 95 |
| abstract_inverted_index.and | 43, 80, 119, 141, 148, 153, 163 |
| abstract_inverted_index.are | 13, 54 |
| abstract_inverted_index.can | 65 |
| abstract_inverted_index.fit | 57 |
| abstract_inverted_index.for | 58, 84 |
| abstract_inverted_index.new | 73 |
| abstract_inverted_index.the | 25, 146, 161, 164 |
| abstract_inverted_index.use | 136 |
| abstract_inverted_index.(vs. | 117 |
| abstract_inverted_index.H/14 | 124 |
| abstract_inverted_index.MoE, | 27 |
| abstract_inverted_index.MoEs | 53 |
| abstract_inverted_index.both | 41 |
| abstract_inverted_index.have | 3 |
| abstract_inverted_index.over | 100 |
| abstract_inverted_index.such | 11, 156 |
| abstract_inverted_index.text | 44 |
| abstract_inverted_index.when | 120 |
| abstract_inverted_index.(with | 125 |
| abstract_inverted_index.78.6% | 113 |
| abstract_inverted_index.LIMoE | 39 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.being | 47 |
| abstract_inverted_index.cost. | 106 |
| abstract_inverted_index.data) | 127 |
| abstract_inverted_index.dense | 101 |
| abstract_inverted_index.learn | 66 |
| abstract_inverted_index.loss. | 52 |
| abstract_inverted_index.model | 34 |
| abstract_inverted_index.since | 62 |
| abstract_inverted_index.time. | 22 |
| abstract_inverted_index.using | 49 |
| abstract_inverted_index.which | 85, 135 |
| abstract_inverted_index.while | 46 |
| abstract_inverted_index.84.1%, | 130 |
| abstract_inverted_index.Across | 92 |
| abstract_inverted_index.LIMoE, | 28, 152 |
| abstract_inverted_index.arise; | 75 |
| abstract_inverted_index.custom | 138 |
| abstract_inverted_index.expert | 63, 82 |
| abstract_inverted_index.images | 42 |
| abstract_inverted_index.larger | 137 |
| abstract_inverted_index.layers | 64 |
| abstract_inverted_index.models | 2, 12, 102 |
| abstract_inverted_index.scaled | 122 |
| abstract_inverted_index.single | 18 |
| abstract_inverted_index.sparse | 30 |
| abstract_inverted_index.76.2%), | 118 |
| abstract_inverted_index.accepts | 40 |
| abstract_inverted_index.analyse | 145 |
| abstract_inverted_index.capable | 35 |
| abstract_inverted_index.experts | 33 |
| abstract_inverted_index.further | 121 |
| abstract_inverted_index.methods | 134 |
| abstract_inverted_index.mixture | 31 |
| abstract_inverted_index.natural | 56 |
| abstract_inverted_index.organic | 165 |
| abstract_inverted_index.present | 24 |
| abstract_inverted_index.propose | 87 |
| abstract_inverted_index.scales, | 94 |
| abstract_inverted_index.scheme. | 91 |
| abstract_inverted_index.trained | 15, 48, 108 |
| abstract_inverted_index.However, | 10, 72 |
| abstract_inverted_index.ImageNet | 115 |
| abstract_inverted_index.accuracy | 116 |
| abstract_inverted_index.achieves | 112, 129 |
| abstract_inverted_index.balanced | 81 |
| abstract_inverted_index.behavior | 150 |
| abstract_inverted_index.domains. | 9 |
| abstract_inverted_index.experts. | 169 |
| abstract_inverted_index.modality | 19 |
| abstract_inverted_index.multiple | 8, 93 |
| abstract_inverted_index.obtained | 4 |
| abstract_inverted_index.schemes. | 143 |
| abstract_inverted_index.training | 78 |
| abstract_inverted_index.CLIP-L/14 | 111 |
| abstract_inverted_index.backbone, | 61 |
| abstract_inverted_index.backbones | 140 |
| abstract_inverted_index.differing | 158 |
| abstract_inverted_index.emergence | 166 |
| abstract_inverted_index.excellent | 5 |
| abstract_inverted_index.learning. | 38 |
| abstract_inverted_index.phenomena | 155 |
| abstract_inverted_index.stability | 79 |
| abstract_inverted_index.treatment | 159 |
| abstract_inverted_index.typically | 14 |
| abstract_inverted_index.zero-shot | 114 |
| abstract_inverted_index.LIMoE-L/16 | 107 |
| abstract_inverted_index.additional | 126 |
| abstract_inverted_index.challenges | 74 |
| abstract_inverted_index.comparable | 131 |
| abstract_inverted_index.comparably | 109 |
| abstract_inverted_index.equivalent | 104 |
| abstract_inverted_index.modalities | 162 |
| abstract_inverted_index.multimodal | 37, 60 |
| abstract_inverted_index.remarkable | 97 |
| abstract_inverted_index.appropriate | 68 |
| abstract_inverted_index.contrastive | 51 |
| abstract_inverted_index.demonstrate | 96, 154 |
| abstract_inverted_index.improvement | 99 |
| abstract_inverted_index.modalities. | 71 |
| abstract_inverted_index.particular, | 77 |
| abstract_inverted_index.performance | 6, 98 |
| abstract_inverted_index.qualitative | 149 |
| abstract_inverted_index.partitioning | 69 |
| abstract_inverted_index.per-modality | 139 |
| abstract_inverted_index.pre-training | 142 |
| abstract_inverted_index.quantitative | 147 |
| abstract_inverted_index.utilization, | 83 |
| abstract_inverted_index.computational | 105 |
| abstract_inverted_index.entropy-based | 89 |
| abstract_inverted_index.Language-Image | 26 |
| abstract_inverted_index.regularization | 90 |
| abstract_inverted_index.simultaneously, | 45 |
| abstract_inverted_index.state-of-the-art | 133 |
| abstract_inverted_index.modality-specific | 168 |
| abstract_inverted_index.sparsely-activated | 1 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.6499999761581421 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |