LGFeb 12, 2022

Robust Deep Semi-Supervised Learning: A Brief Introduction

arXiv:2202.05975v27 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental survey that identifies and categorizes robustness issues in semi-supervised learning for researchers and practitioners dealing with imperfect real-world data.

The paper addresses the vulnerability of deep semi-supervised learning to corrupted unlabeled data, such as distribution mismatches or adversarial attacks, which causes severe performance degradation, and it provides a survey to define and classify these robustness threats.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes