RECORD
Graph-based Semi-supervised Learning: A Comprehensive Review
Machine Learning · Submitted 26 Feb 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Semi-supervised learning (SSL) has tremendous value in practice due to its ability to utilize both labeled data and unlabelled data. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s1 | 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. | background 0.99 | 0.05 | 0.04 | asserted 1.00 |
| s2 | 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. | background 1.00 | 0.08 | 0.06 | asserted 1.00 |
| s3 | 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. | contribution 0.98 | 0.52 | 0.07 | asserted 0.87 |
| s4 | This makes our paper distinct from recent surveys that cover an overall picture of SSL methods while neglecting fundamental understanding of GSSL methods. | gap 0.76 | 0.44 | 0.06 | asserted 1.00 |
| s5 | 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. | contribution 1.00 | 0.92 | 0.35 | asserted 1.00 |
| s6 | Furthermore, we present several potential research directions as future work with insights into this rapidly growing field. | future work 1.00 | 0.83 | 0.08 | asserted 0.74 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
How the literature uses it
7 arXiv papers cite this in 11 sentences
Papers citing it · 9 sentences without a confident label
Cites it as background 2 papers
-
In the field of graph representation learning, graph neural networks have recently received much interest recently [ref] .
HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization · Graph Neural Networks · 1.00
-
This framework represents a simplified version of the so-called transductive Semi-Supervised Learning (SSL) problem on graphs [ref] , where the labels of some nodes on a graph are known and the goal is to predict the labels of the other nodes in the same graph.
Node Regression on Latent Position Random Graphs via Local Averaging · Introduction · 0.98
What it cites · 6 sentences without a confident label
Cites as background 2 papers
-
Other research work on GCN extensions can be found in [ref] [ref] [ref] [ref] [ref] [ref] [ref] [ref] [ref] .
Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning · Neighborhood normalization · 0.94
-
Other research work on GCN extensions can be found in [ref] [ref] [ref] [ref] [ref] [ref] [ref] [ref] [ref] .
Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning · Neighborhood normalization · 0.94
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.