Recent Deep Semi-supervised Learning Approaches and Related Works

TL;DR

This paper reviews recent deep semi-supervised learning methods, emphasizing their underlying assumptions, classifications, and unified approaches, highlighting the importance of leveraging unlabeled data to reduce reliance on large labeled datasets.

Contribution

It provides a comprehensive overview and classification of recent deep semi-supervised learning techniques based on their core assumptions and unified frameworks.

Findings

Deep semi-supervised methods leverage manifold, cluster, and continuity assumptions.

Recent approaches unify multiple semi-supervised ideas into holistic frameworks.

The review highlights the importance of unlabeled data in deep learning.

Abstract

This work proposes an overview of the recent semi-supervised learning approaches and related works. Despite the remarkable success of neural networks in various applications, there exist a few formidable constraints, including the need for a large amount of labeled data. Therefore, semi-supervised learning, which is a learning scheme in which scarce labels and a larger amount of unlabeled data are utilized to train models (e.g., deep neural networks), is getting more important. Based on the key assumptions of semi-supervised learning, which are the manifold assumption, cluster assumption, and continuity assumption, the work reviews the recent semi-supervised learning approaches. In particular, the methods in regard to using deep neural networks in a semi-supervised learning setting are primarily discussed. In addition, the existing works are first classified based on the underlying idea and explained, then the holistic approaches that unify the aforementioned ideas are detailed.