Few-Shot Learning for Knowledge Engineering and Intellectual System

Dear Colleagues,

In recent years, deep learning, as an appealing subfield of machine learning, has been found to be able to extract representations with multiple levels of abstraction to discover intricate structures in data, having produced excellent results in knowledge engineering and intellectual systems. It has dramatically bridged the gap between machines and the human brain due to the powerful ability of representation learning. In essence, deep learning can generalize superior networks by fitting a large number of labeled data and, thus, showing the significant performance. Unfortunately, there might not be enough labeled data available in applications, which cannot guarantee the robustness and generalization of networks. The issue of labeled data scarcity poses great challenges to the intelligent development of machines.

Inspired by the impressive human ability to learn new tasks without large amounts of prior knowledge, few-shot learning was introduced to address this challenge. It utilizes specific learning paradigms to generalize knowledge in small-scale data, which can quickly adapt to novel tasks with the help of other similar tasks and alleviate the issue of labeled data scarcity. Few-shot learning provides an emerging direction for the research of machine learning, and has become a significant topic for developing learning methods for limited data. Therefore, to further promote the intelligent development of machines, there is a pressing need to study novel methods.

This Special Issue focuses on the latest developments of few-shot learning in various fields, such as computer vision, natural language processing, intelligent video recognition, etc. Our expectations regarding contributions are not confined to research concerning the theory and methodology of machine learning, but also involving the deployment of practical applications based on a few samples.

The topics of interest include (but are not limited to) the following areas:

• Few-shot learning towards computer vision.
• Few-shot learning towards natural language processing.
• Few-shot learning towards acoustic signal processing.
• Application deployments of few-shot learning.
• Theoretical studies of few-shot learning.
• New datasets and benchmarks of few-shot learning.
• Self-supervised learning methods.
• Deep unsupervised learning methods.
• Deep semisupervised learning methods.

Prof. Dr. Zhikui Chen
Dr. Xiaodi Huang
Guest Editors

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. Information is an international peer-reviewed open access monthly 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.

• few-shot learning
• unsupervised learning
• semisupervised learning
• intellectual system