Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
Graph Machine Learning for Analyzing Complex Networks
share announcement

Graph Machine Learning for Analyzing Complex Networks

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 3565

Special Issue Editors

Dr. Dongxiao He

E-Mail Website
Guest Editor
School of Computer Science and Technology, Tianjin University, Tianjin 300072, China
Interests: graph data mining; graph machine learning
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Xiankun Zhang

E-Mail Website
Guest Editor
School of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China
Interests: intelligent information processing; social network analysis

Special Issue Information

Dear Colleagues,

Graph Machine learning (GML) is widely applied in a variety of complex network analysis scenarios in the real world, such as network public opinion analysis, new crown virus spread, e-commerce search and recommendation, the latter of which has demonstrated powerful representation learning and prediction capabilities. With the advance of deep learning, particularly GML and graphs, neural networks significantly promote the theory of machine learning and encourage industrial research in a variety of academic areas. This Special Issue primarily focuses on the most recent advances in the models, algorithms, theories, and applications of GML, both in academic and industrial fields. Contributions to this Special Issue may include, but are not limited to, research on progress in the following areas: graph classification, data augmentation, scalability, explainability, oversmoothing, heterophily, spectral methods, expressivity, temporal data, generative models, graph transformers, self-supervision, contrastive learning, adversarial attacks/ robustness, recommender systems, molecules, proteins, and other related theoretical and applied research.

Our goal is to stimulate continuous development in these areas. In order to achieve this objective, we invite authors to submit original research articles, as well as high-quality review articles that reflect the theme of this Special Issue.

Dr. Dongxiao He
Prof. Dr. Xiankun Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • graph machine learning
  • complex network analysis
  • deep learning
  • graph neural networks

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 9217 KiB  
Article
MGATs: Motif-Based Graph Attention Networks
by Jinfang Sheng, Yufeng Zhang, Bin Wang and Yaoxing Chang
Mathematics 2024, 12(2), 293; https://doi.org/10.3390/math12020293 - 16 Jan 2024
Cited by 1 | Viewed by 1690
Abstract
In recent years, graph convolutional neural networks (GCNs) have become a popular research topic due to their outstanding performance in various complex network data mining tasks. However, current research on graph neural networks lacks understanding of the high-order structural features of networks, focusing [...] Read more.
In recent years, graph convolutional neural networks (GCNs) have become a popular research topic due to their outstanding performance in various complex network data mining tasks. However, current research on graph neural networks lacks understanding of the high-order structural features of networks, focusing mostly on node features and first-order neighbor features. This article proposes two new models, MGAT and MGATv2, by introducing high-order structure motifs that frequently appear in networks and combining them with graph attention mechanisms. By introducing a mixed information matrix based on motifs, the generation process of graph attention coefficients is improved, allowing the model to capture higher-order structural features. Compared with the latest research on various graph neural networks, both MGAT and MGATv2 achieve good results in node classification tasks. Furthermore, through various experimental studies on real datasets, we demonstrate that the introduction of network structural motifs can effectively enhance the expressive power of graph neural networks, indicating that both high-order structural features and attribute features are important components of network feature learning. Full article
(This article belongs to the Special Issue Graph Machine Learning for Analyzing Complex Networks)
►▼ Show Figures

Figure 1

13 pages, 770 KiB  
Article
Asymmetric Graph Contrastive Learning
by Xinglong Chang, Jianrong Wang, Rui Guo, Yingkui Wang and Weihao Li
Mathematics 2023, 11(21), 4505; https://doi.org/10.3390/math11214505 - 31 Oct 2023
Cited by 1 | Viewed by 1282
Abstract
Learning effective graph representations in an unsupervised manner is a popular research topic in graph data analysis. Recently, contrastive learning has shown its success in unsupervised graph representation learning. However, how to avoid collapsing solutions for contrastive learning methods remains a critical challenge. [...] Read more.
Learning effective graph representations in an unsupervised manner is a popular research topic in graph data analysis. Recently, contrastive learning has shown its success in unsupervised graph representation learning. However, how to avoid collapsing solutions for contrastive learning methods remains a critical challenge. In this paper, a simple method is proposed to solve this problem for graph representation learning, which is different from existing commonly used techniques (such as negative samples or predictor network). The proposed model mainly relies on an asymmetric design that consists of two graph neural networks (GNNs) with unequal depth layers to learn node representations from two augmented views and defines contrastive loss only based on positive sample pairs. The simple method has lower computational and memory complexity than existing methods. Furthermore, a theoretical analysis proves that the asymmetric design avoids collapsing solutions when training together with a stop-gradient operation. Our method is compared to nine state-of-the-art methods on six real-world datasets to demonstrate its validity and superiority. The ablation experiments further validated the essential role of the asymmetric architecture. Full article
(This article belongs to the Special Issue Graph Machine Learning for Analyzing Complex Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop