RECORD
Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
Machine Learning · Submitted 16 Jun 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The simulations validate that AVGNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task.
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
Our digital world is full of time series and graphs which capture the various aspects of many complex systems. Traditionally, there are respective methods in processing these two different types of data, e.g., Recurrent Neural Network (RNN) and Graph Neural Network (GNN), while in recent years, time series could be mapped to graphs by using the techniques such as Visibility Graph (VG), so that researchers can use graph algorithms to mine the knowledge in time series. Such mapping methods establish a bridge between time series and graphs, and have high potential to facilitate the analysis of various real-world time series. However, the VG method and its variants are just based on fixed rules and thus lack of flexibility, largely limiting their application in reality. In this paper, we propose an Adaptive Visibility Graph (AVG) algorithm that can adaptively map time series into graphs, based on which we further establish an end-to-end classification framework AVGNet, by utilizing GNN model DiffPool as the classifier. We then adopt AVGNet for radio signal modulation classification which is an important task in the field of wireless communication. The simulations validate that AVGNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Our digital world is full of time series and graphs which capture the various aspects of many complex systems. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s1 | Traditionally, there are respective methods in processing these two different types of data, e.g., Recurrent Neural Network (RNN) and Graph Neural Network (GNN), while in recent years, time series could be mapped to graphs by using the techniques such as Visibility Graph (VG), so that researchers can use graph algorithms to mine the knowledge in time series. | background 1.00 | 0.04 | 0.02 | asserted 0.96 |
| s2 | Such mapping methods establish a bridge between time series and graphs, and have high potential to facilitate the analysis of various real-world time series. | background 0.96 | 0.06 | 0.03 | hedged possibility 0.54 |
| s3 | However, the VG method and its variants are just based on fixed rules and thus lack of flexibility, largely limiting their application in reality. | gap 0.87 | 0.07 | 0.02 | asserted 1.00 |
| s4 | In this paper, we propose an Adaptive Visibility Graph (AVG) algorithm that can adaptively map time series into graphs, based on which we further establish an end-to-end classification framework AVGNet, by utilizing GNN model DiffPool as the classifier. | contribution 0.80 | 0.96 | 0.10 | asserted 1.00 |
| s5 | We then adopt AVGNet for radio signal modulation classification which is an important task in the field of wireless communication. | contribution 0.74 | 0.90 | 0.03 | asserted 0.97 |
| s6 | The simulations validate that AVGNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task. | result 1.00 | 0.95 | 0.87 | asserted 1.00 |
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
Our digital world is full of time series and graphs which capture the various aspects of many complex systems. Traditionally, there are respective methods in processing these two different types of data, e.g., Recurrent Neural Network (RNN) and Graph Neural Network (GNN), while in recent years, time series could be mapped to graphs by using the techniques such as Visibility Graph (VG), so that researchers can use graph algorithms to mine the knowledge in time series. Such mapping methods establish a bridge between time series and graphs, and have high potential to facilitate the analysis of various real-world time series. However, the VG method and its variants are just based on fixed rules and thus lack of flexibility, largely limiting their application in reality. In this paper, we propose an Adaptive Visibility Graph (AVG) algorithm that can adaptively map time series into graphs, based on which we further establish an end-to-end classification framework AVGNet, by utilizing GNN model DiffPool as the classifier. We then adopt AVGNet for radio signal modulation classification which is an important task in the field of wireless communication. The simulations validate that AVGNet outperforms a series of advanced deep learning methods, achieving the state-of-the-art performance in this task.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Uses the method or tool of 1 paper
-
In the simulations, we use cross-entropy loss function and Adam [ref] optimizer.
Adam: A Method for Stochastic Optimization · Simulation Setting · 1.00
Cites as background 2 papers
-
The representative methods of graph classification can be divided into three types, the first one is the graph kernel methods, which are mainly based on random walk [ref] , path [ref] and subtree [ref] ; The second one is graph embedding methods, such as subgraph2vec [ref] and graph2vec [ref] ; And the last one is deep learning methods, i.e., Graph Neural Networks (GNNs), which typically includes Dynamic Graph Convolutional Neural Networks (DGCNN) [ref] , DiffPool [ref] and SAGPool [ref] .
subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs · Introduction · 0.95
-
The representative methods of graph classification can be divided into three types, the first one is the graph kernel methods, which are mainly based on random walk [ref] , path [ref] and subtree [ref] ; The second one is graph embedding methods, such as subgraph2vec [ref] and graph2vec [ref] ; And the last one is deep learning methods, i.e., Graph Neural Networks (GNNs), which typically includes Dynamic Graph Convolutional Neural Networks (DGCNN) [ref] , DiffPool [ref] and SAGPool [ref] .
graph2vec: Learning Distributed Representations of Graphs · Introduction · 0.95
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.