Journal
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
Volume 35, Issue 1, Pages 857-876Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2021.3090866
Keywords
Self-supervised learning; generative model; contrastive learning; deep learning
Ask authors/readers for more resources
Deep supervised learning has been successful, but it is limited by manual labels and vulnerable to attacks. In contrast, self-supervised learning utilizes input data as supervision, showing promising performance on representation learning. This survey comprehensively reviews self-supervised learning methods in computer vision, natural language processing, and graph learning.
Deep supervised learning has achieved great success in the last decade. However, its defects of heavy dependence on manual labels and vulnerability to attacks have driven people to find other paradigms. As an alternative, self-supervised learning (SSL) attracts many researchers for its soaring performance on representation learning in the last several years. Self-supervised representation learning leverages input data itself as supervision and benefits almost all types of downstream tasks. In this survey, we take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning. We comprehensively review the existing empirical methods and summarize them into three main categories according to their objectives: generative, contrastive, and generative-contrastive (adversarial). We further collect related theoretical analysis on self-supervised learning to provide deeper thoughts on why self-supervised learning works. Finally, we briefly discuss open problems and future directions for self-supervised learning. An outline slide for the survey is provided(1).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available