Robust Deep Semi-Supervised Learning: A Brief Introduction

by   Lan-Zhe Guo, et al.

Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning performance by leveraging unlabeled data when labels are insufficient. Recently, SSL with deep models has proven to be successful on standard benchmark tasks. However, they are still vulnerable to various robustness threats in real-world applications as these benchmarks provide perfect unlabeled data, while in realistic scenarios, unlabeled data could be corrupted. Many researchers have pointed out that after exploiting corrupted unlabeled data, SSL suffers severe performance degradation problems. Thus, there is an urgent need to develop SSL algorithms that could work robustly with corrupted unlabeled data. To fully understand robust SSL, we conduct a survey study. We first clarify a formal definition of robust SSL from the perspective of machine learning. Then, we classify the robustness threats into three categories: i) distribution corruption, i.e., unlabeled data distribution is mismatched with labeled data; ii) feature corruption, i.e., the features of unlabeled examples are adversarially attacked; and iii) label corruption, i.e., the label distribution of unlabeled data is imbalanced. Under this unified taxonomy, we provide a thorough review and discussion of recent works that focus on these issues. Finally, we propose possible promising directions within robust SSL to provide insights for future research.


page 8

page 9

page 12

page 16

page 17

page 18

page 19

page 20


Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

Semi-supervised learning (SSL) provides a powerful framework for leverag...

Semi-Supervised and Unsupervised Deep Visual Learning: A Survey

State-of-the-art deep learning models are often trained with a large amo...

Robust Semi-Supervised Learning when Labels are Missing at Random

Semi-supervised learning methods are motivated by the relative paucity o...

Applying Self-Supervised Learning to Medicine: Review of the State of the Art and Medical Implementations

Machine learning has become an increasingly ubiquitous technology, as bi...

Unsupervised Feature Ranking via Attribute Networks

The need for learning from unlabeled data is increasing in contemporary ...

Robustness to Adversarial Perturbations in Learning from Incomplete Data

What is the role of unlabeled data in an inference problem, when the pre...

Semi-supervised Learning with Contrastive Predicative Coding

Semi-supervised learning (SSL) provides a powerful framework for leverag...

Please sign up or login with your details

Forgot password? Click here to reset