Developments in Transfer Learning

Dear Colleagues,

There has been a growing interest in transfer learning approaches with the rapid development of deep learning over the past decade. Even though such strategies for leveraging the transferability of knowledge from one domain to another related domain or a subdomain have been around for quite some time in the machine learning literature, large pre-trained deep learning models on large amounts of data from broader domains such as computer vision and NLP have been finetuned with fewer data and limited computational resources for applications in many specific real-world problems, such as medical imaging, etc. However, transfer learning methods have not been extensively studied in tabular data, limiting their applications in many real-world situations, such as financial data, medical history data, etc.

We are organizing this Special Issue to help to promote development in both theoretical aspects and applications of transfer learning in diverse domains. We invite and welcome review, expository, and original research articles dealing with recent theoretical advances in transfer learning techniques and their multidisciplinary applications.

Dr. Sourav Sen
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep transfer learning
• feature extraction
• domain adaptation
• few-shot learning
• zero-shot learning
• fine-tuning
• federated transfer learning
• computer vision
• natural language processing
• pre-trained language models
• medical imaging
• tabular data