Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 45, Issue 4, Pages 4747-4767Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2022.3198175
Keywords
Semisupervised learning; Manifolds; Standards; Geometry; Complexity theory; Task analysis; Supervised learning; Semi-supervised learning; learning theory; improvement guarantees; assumptions
Ask authors/readers for more resources
This survey explores semi-supervised learning and its applications in classification and regression tasks. It summarizes theoretical results and highlights the assumptions made when utilizing unlabeled data. The survey aims to identify the limits and potential benefits of semi-supervised learning, focusing on understanding the underlying theory and assumptions.
Semi-supervised learning is the learning setting in which we have both labeled and unlabeled data at our disposal. This survey covers theoretical results for this setting and maps out the benefits of unlabeled data in classification and regression tasks. Most methods that use unlabeled data rely on certain assumptions about the data distribution. When those assumptions are not met, including unlabeled data may actually decrease performance. For all practical purposes, it is therefore instructive to have an understanding of the underlying theory and the possible learning behavior that comes with it. This survey gathers results about the possible gains one can achieve when using semi-supervised learning as well as results about the limits of such methods. Specifically, it aims to answer the following questions: what are, in terms of improving supervised methods, the limits of semi-supervised learning? What are the assumptions of different methods? What can we achieve if the assumptions are true? As, indeed, the precise assumptions made are of the essence, this is where the survey's particular attention goes out to.
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