Unveiling the power of transfer learning towards efficient artificial intelligence Article Swipe
Large-scale models, abundant data, and dense computation are the pivotal pillars of deep neural networks. The present-day deep learning models have made significant strides in various areas such as Computer Vision (CV), Natural Language Processing (NLP), and Audio Signal Processing (ASP). These technological integrations have notably improved industrial automation while providing considerable enhancements to daily life. However, despite these advancements, deep learning still faces severe challenges in evolving into an efficient and accessible system. One of the major concerns is data efficiency due to the labor-intensive and costly process of annotated data. The other concern is model efficiency, impacting deployment costs and users' accessibility. Transfer Learning (TL) is a promising solution to address these challenges. TL harnesses the power of acquired data and pre-trained models to facilitate applications of new related tasks or smaller models. This dissertation is structured into three primary sections: Feature Transfer Learning, Model Transfer Learning, and Joint Transfer Learning. (1) Feature Transfer Learning (FTL), widely employed in Domain Adaptation (DA), utilizes a shared encoder model to learn universal representations through cross-domain feature alignment loss. It is primarily comprised of Unsupervised Domain Adaptation (UDA) and Semi-supervised Domain Adaptation (SSDA), depending on target label accessibility. The principal technical challenges with FTL involve distribution mismatch across domains and overfitting toward labeled data. To address these issues, this dissertation proposes structural regularization and multi-level alignment. (2) Model Transfer Learning (MTL) focuses on parameter tuning based on pre-trained models for novel tasks. An exemplary application of MTL is Knowledge Distillation (KD), which facilitates knowledge transfer from larger to smaller models for compression. This dissertation introduces a graph-based KD framework that enables real-time graph retrieval. In addition, with the surge of foundation models necessitating efficiency during finetuning, Parameter-Efficient Model Finetuning (PEFT) has received prominence. PEFT has been applied here to enrich a pre-trained tabular model's capacity by injecting external prior knowledge. (3) Joint Transfer Learning (JTL) synergizes FTL and MTL, necessitating both cross-domain feature alignments and parameter tuning. JTL is particularly suitable for instance alignment across different modalities, which helps to build multimodal models without --Author's abstract
Related Topics
Concepts
Metadata
- Type
- dissertation
- Language
- en
- Landing Page
- https://doi.org/10.17760/d20581917
- https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdf
- OA Status
- gold
- References
- 280
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4388764329
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4388764329Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.17760/d20581917Digital Object Identifier
- Title
-
Unveiling the power of transfer learning towards efficient artificial intelligenceWork title
- Type
-
dissertationOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-01-01Full publication date if available
- Authors
-
Can QinList of authors in order
- Landing page
-
https://doi.org/10.17760/d20581917Publisher landing page
- PDF URL
-
https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdfDirect OA link when available
- Concepts
-
Computer science, Transfer of learning, Artificial intelligence, Overfitting, Deep learning, Machine learning, Adaptation (eye), Feature learning, Feature (linguistics), Domain (mathematical analysis), Artificial neural network, Optics, Philosophy, Physics, Mathematical analysis, Linguistics, MathematicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
280Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4388764329 |
|---|---|
| doi | https://doi.org/10.17760/d20581917 |
| ids.doi | https://doi.org/10.17760/d20581917 |
| ids.openalex | https://openalex.org/W4388764329 |
| fwci | |
| type | dissertation |
| title | Unveiling the power of transfer learning towards efficient artificial intelligence |
| 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 | 0.9998999834060669 |
| 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 | 0.9945999979972839 |
| 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 | 0.9937000274658203 |
| 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/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7438133358955383 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C150899416 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7427768111228943 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1820378 |
| concepts[1].display_name | Transfer of learning |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.7212863564491272 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C22019652 |
| concepts[3].level | 3 |
| concepts[3].score | 0.6974925994873047 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q331309 |
| concepts[3].display_name | Overfitting |
| concepts[4].id | https://openalex.org/C108583219 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6705027222633362 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep learning |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.6039592027664185 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C139807058 |
| concepts[6].level | 2 |
| concepts[6].score | 0.47537627816200256 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q352374 |
| concepts[6].display_name | Adaptation (eye) |
| concepts[7].id | https://openalex.org/C59404180 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4728712737560272 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[7].display_name | Feature learning |
| concepts[8].id | https://openalex.org/C2776401178 |
| concepts[8].level | 2 |
| concepts[8].score | 0.464286208152771 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[8].display_name | Feature (linguistics) |
| concepts[9].id | https://openalex.org/C36503486 |
| concepts[9].level | 2 |
| concepts[9].score | 0.41302624344825745 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[9].display_name | Domain (mathematical analysis) |
| concepts[10].id | https://openalex.org/C50644808 |
| concepts[10].level | 2 |
| concepts[10].score | 0.34684500098228455 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[10].display_name | Artificial neural network |
| concepts[11].id | https://openalex.org/C120665830 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[11].display_name | Optics |
| concepts[12].id | https://openalex.org/C138885662 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[12].display_name | Philosophy |
| concepts[13].id | https://openalex.org/C121332964 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[13].display_name | Physics |
| concepts[14].id | https://openalex.org/C134306372 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[14].display_name | Mathematical analysis |
| concepts[15].id | https://openalex.org/C41895202 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[15].display_name | Linguistics |
| concepts[16].id | https://openalex.org/C33923547 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[16].display_name | Mathematics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7438133358955383 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/transfer-of-learning |
| keywords[1].score | 0.7427768111228943 |
| keywords[1].display_name | Transfer of learning |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.7212863564491272 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/overfitting |
| keywords[3].score | 0.6974925994873047 |
| keywords[3].display_name | Overfitting |
| keywords[4].id | https://openalex.org/keywords/deep-learning |
| keywords[4].score | 0.6705027222633362 |
| keywords[4].display_name | Deep learning |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.6039592027664185 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/adaptation |
| keywords[6].score | 0.47537627816200256 |
| keywords[6].display_name | Adaptation (eye) |
| keywords[7].id | https://openalex.org/keywords/feature-learning |
| keywords[7].score | 0.4728712737560272 |
| keywords[7].display_name | Feature learning |
| keywords[8].id | https://openalex.org/keywords/feature |
| keywords[8].score | 0.464286208152771 |
| keywords[8].display_name | Feature (linguistics) |
| keywords[9].id | https://openalex.org/keywords/domain |
| keywords[9].score | 0.41302624344825745 |
| keywords[9].display_name | Domain (mathematical analysis) |
| keywords[10].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[10].score | 0.34684500098228455 |
| keywords[10].display_name | Artificial neural network |
| language | en |
| locations[0].id | doi:10.17760/d20581917 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | dissertation |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.17760/d20581917 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5021042598 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0712-5378 |
| authorships[0].author.display_name | Can Qin |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I12912129 |
| authorships[0].affiliations[0].raw_affiliation_string | Doctor of Philosophy in Electrical and Computer Engineering Northeastern University, July 2023 |
| authorships[0].institutions[0].id | https://openalex.org/I12912129 |
| authorships[0].institutions[0].ror | https://ror.org/04t5xt781 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I12912129 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Northeastern University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Can Qin |
| authorships[0].is_corresponding | True |
| authorships[0].raw_affiliation_strings | Doctor of Philosophy in Electrical and Computer Engineering Northeastern University, July 2023 |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unveiling the power of transfer learning towards efficient artificial intelligence |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9998999834060669 |
| 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/W3099765033, https://openalex.org/W4390929683, https://openalex.org/W4206357785, https://openalex.org/W4281381188, https://openalex.org/W3192840557, https://openalex.org/W2951211570, https://openalex.org/W4375928479, https://openalex.org/W3167935049, https://openalex.org/W3023427754, https://openalex.org/W3131673289 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.17760/d20581917 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | dissertation |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.17760/d20581917 |
| primary_location.id | doi:10.17760/d20581917 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | https://repository.library.northeastern.edu/files/neu:4f21nv811/fulltext.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | dissertation |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.17760/d20581917 |
| publication_date | 2023-01-01 |
| publication_year | 2023 |
| referenced_works | https://openalex.org/W1975844474, https://openalex.org/W4362676195, https://openalex.org/W3034368386, https://openalex.org/W2159583324, https://openalex.org/W4308686330, https://openalex.org/W2561529111, https://openalex.org/W4225541089, https://openalex.org/W4226182655, https://openalex.org/W2329664094, https://openalex.org/W3035231859, https://openalex.org/W2184957013, https://openalex.org/W1920022804, https://openalex.org/W4360886185, https://openalex.org/W2211722331, https://openalex.org/W2766897166, https://openalex.org/W3202310860, https://openalex.org/W2038721957, https://openalex.org/W3165647589, https://openalex.org/W2963372104, https://openalex.org/W2560609797, https://openalex.org/W4286588185, https://openalex.org/W4213004511, https://openalex.org/W2938830017, https://openalex.org/W4362679702, https://openalex.org/W2038484192, https://openalex.org/W3034896171, https://openalex.org/W4287110655, https://openalex.org/W3034644181, https://openalex.org/W2950096400, https://openalex.org/W102708294, https://openalex.org/W4287585425, https://openalex.org/W2998224675, https://openalex.org/W4286242951, https://openalex.org/W3124780165, https://openalex.org/W4318718936, https://openalex.org/W4224035735, https://openalex.org/W3158303960, https://openalex.org/W2102913801, https://openalex.org/W4307079201, https://openalex.org/W4296605845, https://openalex.org/W3099793224, https://openalex.org/W2293363371, https://openalex.org/W3214813796, https://openalex.org/W3136405090, https://openalex.org/W2963966654, https://openalex.org/W2129069237, https://openalex.org/W4285815075, https://openalex.org/W4225932300, https://openalex.org/W2194775991, https://openalex.org/W3162340249, https://openalex.org/W2963645458, https://openalex.org/W3206395542, https://openalex.org/W1821462560, https://openalex.org/W3001387309, https://openalex.org/W4312933868, https://openalex.org/W2991612931, https://openalex.org/W3207727708, https://openalex.org/W4226278401, https://openalex.org/W3009368342, https://openalex.org/W4297733535, https://openalex.org/W4287322060, https://openalex.org/W2149466042, https://openalex.org/W4384820637, https://openalex.org/W4312911498, https://openalex.org/W2981720610, https://openalex.org/W2159291411, https://openalex.org/W2963211188, https://openalex.org/W4312977351, https://openalex.org/W3197393979, https://openalex.org/W3211610484, https://openalex.org/W4296663376, https://openalex.org/W4320855434, https://openalex.org/W2165698076, https://openalex.org/W2594718649, https://openalex.org/W3216237230, https://openalex.org/W2964015378, https://openalex.org/W4312615396, https://openalex.org/W2893113606, https://openalex.org/W3171668871, https://openalex.org/W2966792645, https://openalex.org/W4226348722, https://openalex.org/W2946812986, https://openalex.org/W3153675281, https://openalex.org/W2089685866, https://openalex.org/W3129576130, https://openalex.org/W3039278219, https://openalex.org/W3174632922, https://openalex.org/W1644641054, https://openalex.org/W2340897893, https://openalex.org/W3194856818, https://openalex.org/W2899663614, https://openalex.org/W4288089799, https://openalex.org/W3174086521, https://openalex.org/W2104094955, https://openalex.org/W3206121521, https://openalex.org/W2799162093, https://openalex.org/W2887783173, https://openalex.org/W3214726878, https://openalex.org/W3001197829, https://openalex.org/W4312351187, https://openalex.org/W4293454876, https://openalex.org/W3201065055, https://openalex.org/W2198460228, https://openalex.org/W1988115241, https://openalex.org/W4301206121, https://openalex.org/W2604231067, https://openalex.org/W4287207229, https://openalex.org/W4290944574, https://openalex.org/W4320831569, https://openalex.org/W2896457183, https://openalex.org/W3035591099, https://openalex.org/W3035390927, https://openalex.org/W4288099666, https://openalex.org/W4385567345, https://openalex.org/W2965563623, https://openalex.org/W3105966348, https://openalex.org/W2593768305, https://openalex.org/W2405756170, https://openalex.org/W2767699072, https://openalex.org/W2964110616, https://openalex.org/W2998385486, https://openalex.org/W3166396011, https://openalex.org/W2127795553, https://openalex.org/W4288284086, https://openalex.org/W2963799213, https://openalex.org/W4394828156, https://openalex.org/W3127511859, https://openalex.org/W2964288524, https://openalex.org/W4248915016, https://openalex.org/W2983915252, https://openalex.org/W2609338660, https://openalex.org/W3212280254, https://openalex.org/W2884771968, https://openalex.org/W2594519801, https://openalex.org/W4288357592, https://openalex.org/W2895281799, https://openalex.org/W3099887033, https://openalex.org/W2096943734, https://openalex.org/W2164943005, https://openalex.org/W2158815628, https://openalex.org/W2962711740, https://openalex.org/W2965373594, https://openalex.org/W3035682985, https://openalex.org/W1731081199, https://openalex.org/W1882958252, https://openalex.org/W4366463769, https://openalex.org/W4316135746, https://openalex.org/W3204998121, https://openalex.org/W2786559811, https://openalex.org/W3163806994, https://openalex.org/W4312238419, https://openalex.org/W2964303773, https://openalex.org/W3168867926, https://openalex.org/W2788305286, https://openalex.org/W4224912544, https://openalex.org/W3203810176, https://openalex.org/W2866634454, https://openalex.org/W3175604467, https://openalex.org/W3204510963, https://openalex.org/W3157506437, https://openalex.org/W2147286743, https://openalex.org/W4394671432, https://openalex.org/W4385567093, https://openalex.org/W2970597249, https://openalex.org/W2128053425, https://openalex.org/W3110257065, https://openalex.org/W2942259124, https://openalex.org/W4367061106, https://openalex.org/W2962808524, https://openalex.org/W3094024803, https://openalex.org/W2959300817, https://openalex.org/W2962793481, https://openalex.org/W2963727135, https://openalex.org/W4292779060, https://openalex.org/W3037082750, https://openalex.org/W2997001386, https://openalex.org/W2890479120, https://openalex.org/W4312884055, https://openalex.org/W1861492603, https://openalex.org/W3122137342, https://openalex.org/W4297813615, https://openalex.org/W4322716784, https://openalex.org/W4235765578, https://openalex.org/W2982692821, https://openalex.org/W2982242214, https://openalex.org/W4288419263, https://openalex.org/W2012459404, https://openalex.org/W1690739335, https://openalex.org/W2214409633, https://openalex.org/W4320013936, https://openalex.org/W2995607862, https://openalex.org/W4312261477, https://openalex.org/W3006381853, https://openalex.org/W2735673012, https://openalex.org/W4360892312, https://openalex.org/W3046819526, https://openalex.org/W2561238782, https://openalex.org/W4308350893, https://openalex.org/W3093871477, https://openalex.org/W2432356473, https://openalex.org/W4386076215, https://openalex.org/W2986381065, https://openalex.org/W4296979096, https://openalex.org/W4318824039, https://openalex.org/W1969483458, https://openalex.org/W1597213869, https://openalex.org/W2170607286, https://openalex.org/W4281254227, https://openalex.org/W4226148126, https://openalex.org/W3040522390, https://openalex.org/W4321277285, https://openalex.org/W1605556478, https://openalex.org/W2187089797, https://openalex.org/W3209532394, https://openalex.org/W1522301498, https://openalex.org/W1686810756, https://openalex.org/W2601564443, https://openalex.org/W2964111476, https://openalex.org/W3176445421, https://openalex.org/W4377164421, https://openalex.org/W4308163867, https://openalex.org/W3035140194, https://openalex.org/W2962687275, https://openalex.org/W4224308101, https://openalex.org/W2795155917, https://openalex.org/W4327992912, https://openalex.org/W4385245566, https://openalex.org/W4297775537, https://openalex.org/W2983064130, https://openalex.org/W4281485151, https://openalex.org/W4225102763, https://openalex.org/W3165753548, https://openalex.org/W2963121255, https://openalex.org/W1497673662, https://openalex.org/W4385572405, https://openalex.org/W1665214252, https://openalex.org/W4221160819, https://openalex.org/W4295312788, https://openalex.org/W4386075597, https://openalex.org/W4380926676, https://openalex.org/W2963719070, https://openalex.org/W4375869211, https://openalex.org/W1901129140, https://openalex.org/W4306820534, https://openalex.org/W3094235867, https://openalex.org/W2986015886, https://openalex.org/W3124987929, https://openalex.org/W3120044914, https://openalex.org/W3171723960, https://openalex.org/W2995557627, https://openalex.org/W2627183927, https://openalex.org/W1552362697, https://openalex.org/W2950991149, https://openalex.org/W2932167762, https://openalex.org/W4319165322, https://openalex.org/W4382450208, https://openalex.org/W3035576098, https://openalex.org/W4283388932, https://openalex.org/W2908510526, https://openalex.org/W3036167779, https://openalex.org/W3100353583, https://openalex.org/W2963140444, https://openalex.org/W4287121833, https://openalex.org/W4306317252, https://openalex.org/W4225012888, https://openalex.org/W2799132636, https://openalex.org/W2987509417, https://openalex.org/W4360884927, https://openalex.org/W3014788410, https://openalex.org/W2938061533, https://openalex.org/W2963118547, https://openalex.org/W2964139811, https://openalex.org/W4226138446, https://openalex.org/W2604795503, https://openalex.org/W2398606196, https://openalex.org/W2955192706, https://openalex.org/W4226125322, https://openalex.org/W4294558607, https://openalex.org/W3151929433, https://openalex.org/W2137983211 |
| referenced_works_count | 280 |
| abstract_inverted_index.a | 108, 165, 264, 299 |
| abstract_inverted_index.An | 241 |
| abstract_inverted_index.In | 273 |
| abstract_inverted_index.It | 178 |
| abstract_inverted_index.KD | 266 |
| abstract_inverted_index.TL | 115 |
| abstract_inverted_index.To | 213 |
| abstract_inverted_index.an | 69 |
| abstract_inverted_index.as | 28 |
| abstract_inverted_index.by | 304 |
| abstract_inverted_index.in | 24, 66, 160 |
| abstract_inverted_index.is | 79, 95, 107, 137, 179, 246, 327 |
| abstract_inverted_index.of | 11, 75, 89, 119, 128, 182, 244, 278 |
| abstract_inverted_index.on | 193, 231, 235 |
| abstract_inverted_index.or | 132 |
| abstract_inverted_index.to | 53, 83, 111, 125, 169, 256, 297, 338 |
| abstract_inverted_index.(1) | 153 |
| abstract_inverted_index.(2) | 225 |
| abstract_inverted_index.(3) | 309 |
| abstract_inverted_index.FTL | 202, 315 |
| abstract_inverted_index.JTL | 326 |
| abstract_inverted_index.MTL | 245 |
| abstract_inverted_index.One | 74 |
| abstract_inverted_index.The | 15, 92, 197 |
| abstract_inverted_index.and | 4, 36, 71, 86, 101, 122, 149, 187, 208, 222, 316, 323 |
| abstract_inverted_index.are | 7 |
| abstract_inverted_index.due | 82 |
| abstract_inverted_index.for | 238, 259, 330 |
| abstract_inverted_index.has | 289, 293 |
| abstract_inverted_index.new | 129 |
| abstract_inverted_index.the | 8, 76, 84, 117, 276 |
| abstract_inverted_index.(TL) | 106 |
| abstract_inverted_index.MTL, | 317 |
| abstract_inverted_index.PEFT | 292 |
| abstract_inverted_index.This | 135, 261 |
| abstract_inverted_index.been | 294 |
| abstract_inverted_index.both | 319 |
| abstract_inverted_index.data | 80, 121 |
| abstract_inverted_index.deep | 12, 17, 60 |
| abstract_inverted_index.from | 254 |
| abstract_inverted_index.have | 20, 44 |
| abstract_inverted_index.here | 296 |
| abstract_inverted_index.into | 68, 139 |
| abstract_inverted_index.made | 21 |
| abstract_inverted_index.such | 27 |
| abstract_inverted_index.that | 268 |
| abstract_inverted_index.this | 217 |
| abstract_inverted_index.with | 201, 275 |
| abstract_inverted_index.(CV), | 31 |
| abstract_inverted_index.(DA), | 163 |
| abstract_inverted_index.(JTL) | 313 |
| abstract_inverted_index.(KD), | 249 |
| abstract_inverted_index.(MTL) | 229 |
| abstract_inverted_index.(UDA) | 186 |
| abstract_inverted_index.Audio | 37 |
| abstract_inverted_index.Joint | 150, 310 |
| abstract_inverted_index.Model | 146, 226, 286 |
| abstract_inverted_index.These | 41 |
| abstract_inverted_index.areas | 26 |
| abstract_inverted_index.based | 234 |
| abstract_inverted_index.build | 339 |
| abstract_inverted_index.costs | 100 |
| abstract_inverted_index.daily | 54 |
| abstract_inverted_index.data, | 3 |
| abstract_inverted_index.data. | 91, 212 |
| abstract_inverted_index.dense | 5 |
| abstract_inverted_index.faces | 63 |
| abstract_inverted_index.graph | 271 |
| abstract_inverted_index.helps | 337 |
| abstract_inverted_index.label | 195 |
| abstract_inverted_index.learn | 170 |
| abstract_inverted_index.life. | 55 |
| abstract_inverted_index.loss. | 177 |
| abstract_inverted_index.major | 77 |
| abstract_inverted_index.model | 96, 168 |
| abstract_inverted_index.novel | 239 |
| abstract_inverted_index.other | 93 |
| abstract_inverted_index.power | 118 |
| abstract_inverted_index.prior | 307 |
| abstract_inverted_index.still | 62 |
| abstract_inverted_index.surge | 277 |
| abstract_inverted_index.tasks | 131 |
| abstract_inverted_index.these | 58, 113, 215 |
| abstract_inverted_index.three | 140 |
| abstract_inverted_index.which | 250, 336 |
| abstract_inverted_index.while | 49 |
| abstract_inverted_index.(ASP). | 40 |
| abstract_inverted_index.(FTL), | 157 |
| abstract_inverted_index.(NLP), | 35 |
| abstract_inverted_index.(PEFT) | 288 |
| abstract_inverted_index.Domain | 161, 184, 189 |
| abstract_inverted_index.Signal | 38 |
| abstract_inverted_index.Vision | 30 |
| abstract_inverted_index.across | 206, 333 |
| abstract_inverted_index.costly | 87 |
| abstract_inverted_index.during | 283 |
| abstract_inverted_index.enrich | 298 |
| abstract_inverted_index.larger | 255 |
| abstract_inverted_index.models | 19, 124, 237, 258, 280, 341 |
| abstract_inverted_index.neural | 13 |
| abstract_inverted_index.severe | 64 |
| abstract_inverted_index.shared | 166 |
| abstract_inverted_index.target | 194 |
| abstract_inverted_index.tasks. | 240 |
| abstract_inverted_index.toward | 210 |
| abstract_inverted_index.tuning | 233 |
| abstract_inverted_index.users' | 102 |
| abstract_inverted_index.widely | 158 |
| abstract_inverted_index.(SSDA), | 191 |
| abstract_inverted_index.Feature | 143, 154 |
| abstract_inverted_index.Natural | 32 |
| abstract_inverted_index.address | 112, 214 |
| abstract_inverted_index.applied | 295 |
| abstract_inverted_index.concern | 94 |
| abstract_inverted_index.despite | 57 |
| abstract_inverted_index.domains | 207 |
| abstract_inverted_index.enables | 269 |
| abstract_inverted_index.encoder | 167 |
| abstract_inverted_index.feature | 175, 321 |
| abstract_inverted_index.focuses | 230 |
| abstract_inverted_index.involve | 203 |
| abstract_inverted_index.issues, | 216 |
| abstract_inverted_index.labeled | 211 |
| abstract_inverted_index.model's | 302 |
| abstract_inverted_index.models, | 1 |
| abstract_inverted_index.models. | 134 |
| abstract_inverted_index.notably | 45 |
| abstract_inverted_index.pillars | 10 |
| abstract_inverted_index.pivotal | 9 |
| abstract_inverted_index.primary | 141 |
| abstract_inverted_index.process | 88 |
| abstract_inverted_index.related | 130 |
| abstract_inverted_index.smaller | 133, 257 |
| abstract_inverted_index.strides | 23 |
| abstract_inverted_index.system. | 73 |
| abstract_inverted_index.tabular | 301 |
| abstract_inverted_index.through | 173 |
| abstract_inverted_index.tuning. | 325 |
| abstract_inverted_index.various | 25 |
| abstract_inverted_index.without | 342 |
| abstract_inverted_index.Computer | 29 |
| abstract_inverted_index.However, | 56 |
| abstract_inverted_index.Language | 33 |
| abstract_inverted_index.Learning | 105, 156, 228, 312 |
| abstract_inverted_index.Transfer | 104, 144, 147, 151, 155, 227, 311 |
| abstract_inverted_index.abstract | 344 |
| abstract_inverted_index.abundant | 2 |
| abstract_inverted_index.acquired | 120 |
| abstract_inverted_index.capacity | 303 |
| abstract_inverted_index.concerns | 78 |
| abstract_inverted_index.employed | 159 |
| abstract_inverted_index.evolving | 67 |
| abstract_inverted_index.external | 306 |
| abstract_inverted_index.improved | 46 |
| abstract_inverted_index.instance | 331 |
| abstract_inverted_index.learning | 18, 61 |
| abstract_inverted_index.mismatch | 205 |
| abstract_inverted_index.proposes | 219 |
| abstract_inverted_index.received | 290 |
| abstract_inverted_index.solution | 110 |
| abstract_inverted_index.suitable | 329 |
| abstract_inverted_index.transfer | 253 |
| abstract_inverted_index.utilizes | 164 |
| abstract_inverted_index.Knowledge | 247 |
| abstract_inverted_index.Learning, | 145, 148 |
| abstract_inverted_index.Learning. | 152 |
| abstract_inverted_index.addition, | 274 |
| abstract_inverted_index.alignment | 176, 332 |
| abstract_inverted_index.annotated | 90 |
| abstract_inverted_index.comprised | 181 |
| abstract_inverted_index.depending | 192 |
| abstract_inverted_index.different | 334 |
| abstract_inverted_index.efficient | 70 |
| abstract_inverted_index.exemplary | 242 |
| abstract_inverted_index.framework | 267 |
| abstract_inverted_index.harnesses | 116 |
| abstract_inverted_index.impacting | 98 |
| abstract_inverted_index.injecting | 305 |
| abstract_inverted_index.knowledge | 252 |
| abstract_inverted_index.networks. | 14 |
| abstract_inverted_index.parameter | 232, 324 |
| abstract_inverted_index.primarily | 180 |
| abstract_inverted_index.principal | 198 |
| abstract_inverted_index.promising | 109 |
| abstract_inverted_index.providing | 50 |
| abstract_inverted_index.real-time | 270 |
| abstract_inverted_index.sections: | 142 |
| abstract_inverted_index.technical | 199 |
| abstract_inverted_index.universal | 171 |
| abstract_inverted_index.--Author's | 343 |
| abstract_inverted_index.Adaptation | 162, 185, 190 |
| abstract_inverted_index.Finetuning | 287 |
| abstract_inverted_index.Processing | 34, 39 |
| abstract_inverted_index.accessible | 72 |
| abstract_inverted_index.alignment. | 224 |
| abstract_inverted_index.alignments | 322 |
| abstract_inverted_index.automation | 48 |
| abstract_inverted_index.challenges | 65, 200 |
| abstract_inverted_index.deployment | 99 |
| abstract_inverted_index.efficiency | 81, 282 |
| abstract_inverted_index.facilitate | 126 |
| abstract_inverted_index.foundation | 279 |
| abstract_inverted_index.industrial | 47 |
| abstract_inverted_index.introduces | 263 |
| abstract_inverted_index.knowledge. | 308 |
| abstract_inverted_index.multimodal | 340 |
| abstract_inverted_index.retrieval. | 272 |
| abstract_inverted_index.structural | 220 |
| abstract_inverted_index.structured | 138 |
| abstract_inverted_index.synergizes | 314 |
| abstract_inverted_index.Large-scale | 0 |
| abstract_inverted_index.application | 243 |
| abstract_inverted_index.challenges. | 114 |
| abstract_inverted_index.computation | 6 |
| abstract_inverted_index.efficiency, | 97 |
| abstract_inverted_index.facilitates | 251 |
| abstract_inverted_index.finetuning, | 284 |
| abstract_inverted_index.graph-based | 265 |
| abstract_inverted_index.modalities, | 335 |
| abstract_inverted_index.multi-level | 223 |
| abstract_inverted_index.overfitting | 209 |
| abstract_inverted_index.pre-trained | 123, 236, 300 |
| abstract_inverted_index.present-day | 16 |
| abstract_inverted_index.prominence. | 291 |
| abstract_inverted_index.significant | 22 |
| abstract_inverted_index.Distillation | 248 |
| abstract_inverted_index.Unsupervised | 183 |
| abstract_inverted_index.applications | 127 |
| abstract_inverted_index.compression. | 260 |
| abstract_inverted_index.considerable | 51 |
| abstract_inverted_index.cross-domain | 174, 320 |
| abstract_inverted_index.dissertation | 136, 218, 262 |
| abstract_inverted_index.distribution | 204 |
| abstract_inverted_index.enhancements | 52 |
| abstract_inverted_index.integrations | 43 |
| abstract_inverted_index.particularly | 328 |
| abstract_inverted_index.advancements, | 59 |
| abstract_inverted_index.necessitating | 281, 318 |
| abstract_inverted_index.technological | 42 |
| abstract_inverted_index.accessibility. | 103, 196 |
| abstract_inverted_index.regularization | 221 |
| abstract_inverted_index.Semi-supervised | 188 |
| abstract_inverted_index.labor-intensive | 85 |
| abstract_inverted_index.representations | 172 |
| abstract_inverted_index.Parameter-Efficient | 285 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5021042598 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 1 |
| corresponding_institution_ids | https://openalex.org/I12912129 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/8 |
| sustainable_development_goals[0].score | 0.5 |
| sustainable_development_goals[0].display_name | Decent work and economic growth |
| citation_normalized_percentile |