An information-Theoretic Approach to Semi-supervised Transfer Learning Article Swipe
Daniel Jakubovitz
,
David Uliel
,
Miguel Tréfaut Rodrigues
,
Raja Giryes
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.06731
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2306.06731
Transfer learning is a valuable tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet, discrepancies between the underlying distributions of the source and target data are commonplace and are known to have a substantial impact on algorithm performance. In this work we suggest novel information-theoretic approaches for the analysis of the performance of deep neural networks in the context of transfer learning. We focus on the task of semi-supervised transfer learning, in which unlabeled samples from the target dataset are available during network training on the source dataset. Our theory suggests that one may improve the transferability of a deep neural network by incorporating regularization terms on the target data based on information-theoretic quantities, namely the Mutual Information and the Lautum Information. We demonstrate the effectiveness of the proposed approaches in various semi-supervised transfer learning experiments.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2306.06731
- https://arxiv.org/pdf/2306.06731
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4380558421
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4380558421Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2306.06731Digital Object Identifier
- Title
-
An information-Theoretic Approach to Semi-supervised Transfer LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-06-11Full publication date if available
- Authors
-
Daniel Jakubovitz, David Uliel, Miguel Tréfaut Rodrigues, Raja GiryesList of authors in order
- Landing page
-
https://arxiv.org/abs/2306.06731Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2306.06731Direct 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/2306.06731Direct OA link when available
- Concepts
-
Transfer of learning, Computer science, Artificial intelligence, Machine learning, Transferability, Deep learning, Regularization (linguistics), Artificial neural network, Context (archaeology), Labeled data, Semi-supervised learning, Supervised learning, Deep neural networks, Logit, Biology, PaleontologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4380558421 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2306.06731 |
| ids.doi | https://doi.org/10.48550/arxiv.2306.06731 |
| ids.openalex | https://openalex.org/W4380558421 |
| fwci | |
| type | preprint |
| title | An information-Theoretic Approach to Semi-supervised Transfer Learning |
| 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 | 0.9969000220298767 |
| 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/T11609 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9573000073432922 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2212 |
| topics[1].subfield.display_name | Ocean Engineering |
| topics[1].display_name | Geophysical Methods and Applications |
| topics[2].id | https://openalex.org/T10201 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9419000148773193 |
| 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 | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C150899416 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8014212846755981 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1820378 |
| concepts[0].display_name | Transfer of learning |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.749965250492096 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.7055720686912537 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C119857082 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6465377807617188 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[3].display_name | Machine learning |
| concepts[4].id | https://openalex.org/C61272859 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6011431813240051 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7834031 |
| concepts[4].display_name | Transferability |
| concepts[5].id | https://openalex.org/C108583219 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5475245714187622 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[5].display_name | Deep learning |
| concepts[6].id | https://openalex.org/C2776135515 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5146032571792603 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q17143721 |
| concepts[6].display_name | Regularization (linguistics) |
| concepts[7].id | https://openalex.org/C50644808 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5126768350601196 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[7].display_name | Artificial neural network |
| concepts[8].id | https://openalex.org/C2779343474 |
| concepts[8].level | 2 |
| concepts[8].score | 0.49796128273010254 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[8].display_name | Context (archaeology) |
| concepts[9].id | https://openalex.org/C2776145971 |
| concepts[9].level | 2 |
| concepts[9].score | 0.45422792434692383 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q30673951 |
| concepts[9].display_name | Labeled data |
| concepts[10].id | https://openalex.org/C58973888 |
| concepts[10].level | 2 |
| concepts[10].score | 0.45203864574432373 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1041418 |
| concepts[10].display_name | Semi-supervised learning |
| concepts[11].id | https://openalex.org/C136389625 |
| concepts[11].level | 3 |
| concepts[11].score | 0.45141178369522095 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q334384 |
| concepts[11].display_name | Supervised learning |
| concepts[12].id | https://openalex.org/C2984842247 |
| concepts[12].level | 3 |
| concepts[12].score | 0.41903793811798096 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[12].display_name | Deep neural networks |
| concepts[13].id | https://openalex.org/C140331021 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q1868104 |
| concepts[13].display_name | Logit |
| concepts[14].id | https://openalex.org/C86803240 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[14].display_name | Biology |
| concepts[15].id | https://openalex.org/C151730666 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[15].display_name | Paleontology |
| keywords[0].id | https://openalex.org/keywords/transfer-of-learning |
| keywords[0].score | 0.8014212846755981 |
| keywords[0].display_name | Transfer of learning |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.749965250492096 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.7055720686912537 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/machine-learning |
| keywords[3].score | 0.6465377807617188 |
| keywords[3].display_name | Machine learning |
| keywords[4].id | https://openalex.org/keywords/transferability |
| keywords[4].score | 0.6011431813240051 |
| keywords[4].display_name | Transferability |
| keywords[5].id | https://openalex.org/keywords/deep-learning |
| keywords[5].score | 0.5475245714187622 |
| keywords[5].display_name | Deep learning |
| keywords[6].id | https://openalex.org/keywords/regularization |
| keywords[6].score | 0.5146032571792603 |
| keywords[6].display_name | Regularization (linguistics) |
| keywords[7].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[7].score | 0.5126768350601196 |
| keywords[7].display_name | Artificial neural network |
| keywords[8].id | https://openalex.org/keywords/context |
| keywords[8].score | 0.49796128273010254 |
| keywords[8].display_name | Context (archaeology) |
| keywords[9].id | https://openalex.org/keywords/labeled-data |
| keywords[9].score | 0.45422792434692383 |
| keywords[9].display_name | Labeled data |
| keywords[10].id | https://openalex.org/keywords/semi-supervised-learning |
| keywords[10].score | 0.45203864574432373 |
| keywords[10].display_name | Semi-supervised learning |
| keywords[11].id | https://openalex.org/keywords/supervised-learning |
| keywords[11].score | 0.45141178369522095 |
| keywords[11].display_name | Supervised learning |
| keywords[12].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[12].score | 0.41903793811798096 |
| keywords[12].display_name | Deep neural networks |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2306.06731 |
| 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/2306.06731 |
| 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/2306.06731 |
| locations[1].id | doi:10.48550/arxiv.2306.06731 |
| 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.2306.06731 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5027176174 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7368-2370 |
| authorships[0].author.display_name | Daniel Jakubovitz |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jakubovitz, Daniel |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5092160831 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | David Uliel |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Uliel, David |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5026028064 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3958-9919 |
| authorships[2].author.display_name | Miguel Tréfaut Rodrigues |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Rodrigues, Miguel |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5072571599 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-2830-0297 |
| authorships[3].author.display_name | Raja Giryes |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Giryes, Raja |
| authorships[3].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/2306.06731 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | An information-Theoretic Approach to Semi-supervised Transfer 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 | 0.9969000220298767 |
| 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/W4312414840, https://openalex.org/W34092691, https://openalex.org/W2794908468, https://openalex.org/W4206276646, https://openalex.org/W2943467239, https://openalex.org/W1571801203, https://openalex.org/W101422005, https://openalex.org/W192740413, https://openalex.org/W3004135598, https://openalex.org/W2952937263 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2306.06731 |
| 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/2306.06731 |
| 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/2306.06731 |
| primary_location.id | pmh:oai:arXiv.org:2306.06731 |
| 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/2306.06731 |
| 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/2306.06731 |
| publication_date | 2023-06-11 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 3, 27, 55, 121 |
| abstract_inverted_index.In | 61 |
| abstract_inverted_index.We | 85, 145 |
| abstract_inverted_index.as | 9 |
| abstract_inverted_index.by | 125 |
| abstract_inverted_index.in | 6, 23, 33, 79, 94, 153 |
| abstract_inverted_index.is | 2 |
| abstract_inverted_index.it | 10 |
| abstract_inverted_index.of | 26, 30, 42, 72, 75, 82, 90, 120, 149 |
| abstract_inverted_index.on | 58, 87, 107, 129, 134 |
| abstract_inverted_index.to | 18, 53 |
| abstract_inverted_index.we | 64 |
| abstract_inverted_index.Our | 111 |
| abstract_inverted_index.and | 45, 50, 141 |
| abstract_inverted_index.are | 48, 51, 102 |
| abstract_inverted_index.for | 69 |
| abstract_inverted_index.may | 116 |
| abstract_inverted_index.one | 15, 115 |
| abstract_inverted_index.the | 24, 34, 39, 43, 70, 73, 80, 88, 99, 108, 118, 130, 138, 142, 147, 150 |
| abstract_inverted_index.Yet, | 36 |
| abstract_inverted_index.case | 25 |
| abstract_inverted_index.data | 47, 132 |
| abstract_inverted_index.deep | 7, 76, 122 |
| abstract_inverted_index.from | 14, 98 |
| abstract_inverted_index.have | 54 |
| abstract_inverted_index.task | 89 |
| abstract_inverted_index.that | 114 |
| abstract_inverted_index.this | 62 |
| abstract_inverted_index.tool | 5 |
| abstract_inverted_index.work | 63 |
| abstract_inverted_index.based | 133 |
| abstract_inverted_index.focus | 86 |
| abstract_inverted_index.known | 52 |
| abstract_inverted_index.novel | 66 |
| abstract_inverted_index.small | 28 |
| abstract_inverted_index.terms | 128 |
| abstract_inverted_index.which | 95 |
| abstract_inverted_index.Lautum | 143 |
| abstract_inverted_index.Mutual | 139 |
| abstract_inverted_index.allows | 11 |
| abstract_inverted_index.during | 104 |
| abstract_inverted_index.impact | 57 |
| abstract_inverted_index.namely | 137 |
| abstract_inverted_index.neural | 77, 123 |
| abstract_inverted_index.number | 29 |
| abstract_inverted_index.source | 44, 109 |
| abstract_inverted_index.target | 46, 100, 131 |
| abstract_inverted_index.theory | 112 |
| abstract_inverted_index."source | 16 |
| abstract_inverted_index."target | 20 |
| abstract_inverted_index.another | 19 |
| abstract_inverted_index.between | 38 |
| abstract_inverted_index.context | 81 |
| abstract_inverted_index.dataset | 101 |
| abstract_inverted_index.improve | 117 |
| abstract_inverted_index.latter. | 35 |
| abstract_inverted_index.network | 105, 124 |
| abstract_inverted_index.samples | 97 |
| abstract_inverted_index.suggest | 65 |
| abstract_inverted_index.various | 154 |
| abstract_inverted_index.Transfer | 0 |
| abstract_inverted_index.analysis | 71 |
| abstract_inverted_index.dataset" | 17 |
| abstract_inverted_index.dataset. | 110 |
| abstract_inverted_index.examples | 32 |
| abstract_inverted_index.learning | 1, 8, 157 |
| abstract_inverted_index.networks | 78 |
| abstract_inverted_index.proposed | 151 |
| abstract_inverted_index.suggests | 113 |
| abstract_inverted_index.training | 31, 106 |
| abstract_inverted_index.transfer | 83, 92, 156 |
| abstract_inverted_index.valuable | 4 |
| abstract_inverted_index.algorithm | 59 |
| abstract_inverted_index.available | 103 |
| abstract_inverted_index.dataset", | 21 |
| abstract_inverted_index.learning, | 93 |
| abstract_inverted_index.learning. | 84 |
| abstract_inverted_index.unlabeled | 96 |
| abstract_inverted_index.approaches | 68, 152 |
| abstract_inverted_index.especially | 22 |
| abstract_inverted_index.underlying | 40 |
| abstract_inverted_index.Information | 140 |
| abstract_inverted_index.commonplace | 49 |
| abstract_inverted_index.demonstrate | 146 |
| abstract_inverted_index.information | 13 |
| abstract_inverted_index.performance | 74 |
| abstract_inverted_index.propagating | 12 |
| abstract_inverted_index.quantities, | 136 |
| abstract_inverted_index.substantial | 56 |
| abstract_inverted_index.Information. | 144 |
| abstract_inverted_index.experiments. | 158 |
| abstract_inverted_index.performance. | 60 |
| abstract_inverted_index.discrepancies | 37 |
| abstract_inverted_index.distributions | 41 |
| abstract_inverted_index.effectiveness | 148 |
| abstract_inverted_index.incorporating | 126 |
| abstract_inverted_index.regularization | 127 |
| abstract_inverted_index.semi-supervised | 91, 155 |
| abstract_inverted_index.transferability | 119 |
| abstract_inverted_index.information-theoretic | 67, 135 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |