Result: Declarative, generic definition and effective implementation of transfer learning algorithms

Title:
Declarative, generic definition and effective implementation of transfer learning algorithms
Contributors:
Department of Computer Science (University of Mascara), Université Mustapha Stambouli de Mascara [Algérie] = University Mustapha Stambouli [Mascara, Algeria] (UMSM), Institut Supérieur d'Informatique et de Mathématiques de Monastir (ISIMM), جامعة المنستير - Université de Monastir - University of Monastir (UM), Département Automatique, Productique et Informatique (IMT Atlantique - DAPI), IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Software Stack for Massively Geo-Distributed Infrastructures (STACK), Centre Inria de l'Université de Rennes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Orange S.A.-Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-NANTES UNIVERSITÉ - École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Nantes Université (Nantes Univ), Springer, ANR-23-PECL-0006,SPIREC,Supervision et Prédiction multi-niveaux pour Infrasctructures géo-distribuées et hétérogènes dans le continuum Cloud/Edge/IoT(2023)
Source:
AIAI 2025 - 21st International Conference on Artificial Intelligence Applications and Innovations. :1-14
Publisher Information:
CCSD, 2025.
Publication Year:
2025
Collection:
collection:CNRS
collection:INRIA
collection:EC-NANTES
collection:INRIA-RENNES
collection:INRIA_TEST
collection:UNAM
collection:TESTALAIN1
collection:INRIA2
collection:LS2N
collection:LS2N-STACK
collection:LS2N-STACK-IMTA
collection:IMTA_DAPI
collection:LS2N-IMTA
collection:INRIA-RENGRE
collection:IMT-ATLANTIQUE
collection:INSTITUTS-TELECOM
collection:ANR
collection:NANTES-UNIVERSITE
collection:NANTES-UNIV
collection:INSTITUT-MINES-TELECOM
Subject Geographic:
Original Identifier:
HAL: hal-05005665
Document Type:
Conference conferenceObject<br />Conference papers
Language:
English
Rights:
info:eu-repo/semantics/OpenAccess
URL: http://creativecommons.org/licenses/by/
Accession Number:
edshal.hal.05005665v3
Database:
HAL

Further Information

Machine learning, especially deep learning, has become es- sential in many application domains. However, deep learning relies on artificial neural networks that often face resource-related limitations. For instance, data is often proprietary, model training can be costly, and using these models may be constrained by limited computational or storage resources. Transfer learning offers a solution to overcome these constraints by "transferring" a model from a source domain to a target domain, potentially in a different context. This transfer takes various forms: models can be adapted with minor structural changes (e.g., "fine- tuning"), reduced in size (e.g., "knowledge distillation"), or retrained with modified training and testing datasets (e.g., "domain adaptation"). This paper first motivates the need for a generic definitional framework and implementation support for transfer learning through a literature review. We then introduce Generic Transfer Learning (GTL), our pro- posal of such a framework. GTL supports the declarative definition of transfers through network transformations and dataset manipulations and includes corresponding Python implementation support. We finally present a case study demonstrating how to define and implement a trans- fer using GTL in the health domain.