Graph-based Semi-supervised Learning: A Comprehensive Review

TL;DR

This comprehensive review explores graph-based semi-supervised learning (GSSL), detailing its methods, taxonomy, applications, and future research directions, providing valuable insights for researchers and practitioners.

Contribution

The paper introduces a new generalized taxonomy for GSSL, covering recent advances, and offers a systematic understanding of graph regularization and embedding methods.

Findings

GSSL effectively leverages graph structures for semi-supervised learning.

The taxonomy unifies various GSSL approaches under a common framework.

The paper highlights key datasets, codes, and applications in GSSL.

Abstract

Semi-supervised learning (SSL) has tremendous value in practice due to its ability to utilize both labeled data and unlabelled data. An important class of SSL methods is to naturally represent data as graphs such that the label information of unlabelled samples can be inferred from the graphs, which corresponds to graph-based semi-supervised learning (GSSL) methods. GSSL methods have demonstrated their advantages in various domains due to their uniqueness of structure, the universality of applications, and their scalability to large scale data. Focusing on this class of methods, this work aims to provide both researchers and practitioners with a solid and systematic understanding of relevant advances as well as the underlying connections among them. This makes our paper distinct from recent surveys that cover an overall picture of SSL methods while neglecting fundamental understanding of GSSL methods. In particular, a major contribution of this paper lies in a new generalized taxonomy for GSSL, including graph regularization and graph embedding methods, with the most up-to-date references and useful resources such as codes, datasets, and applications. Furthermore, we present several potential research directions as future work with insights into this rapidly growing field.