A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

Deep learning has seen significant growth recently and is now applied to a wide range of conventional use cases, including graphs. Graph data provides relational information between elements and is a standard data format for various machine learning and deep learning tasks. Models that can learn fro...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of big data Ročník 11; číslo 1; s. 18 - 43
Hlavní autori: Khemani, Bharti, Patil, Shruti, Kotecha, Ketan, Tanwar, Sudeep
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 16.01.2024
Springer Nature B.V
SpringerOpen
Predmet:
Application
Big Data
Case Study
Cognitive tasks
Communications Engineering
Computational Science and Engineering
Computer Science
Data
Data Mining and Knowledge Discovery
Database Management
Datasets
Deep learning
Educational activities
Graph Attention Networks (GAT)
Graph Convolution Network (GCN)
Graph Neural Network (GNN)
Graph neural networks
Graph theory
Graphs
GraphSAGE
Information Storage and Retrieval
Libraries
Machine learning
Mathematical Applications in Computer Science
Message passing
Message Passing Mechanism
Natural Language Processing (NLP)
Networks
Neural networks
Nodes
Standard data
Graph Neural Network (GNN)
Graph Attention Networks (GAT)
GraphSAGE
Message Passing Mechanism
Natural Language Processing (NLP)
Graph Convolution Network (GCN)
ISSN:2196-1115, 2196-1115
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Deep learning has seen significant growth recently and is now applied to a wide range of conventional use cases, including graphs. Graph data provides relational information between elements and is a standard data format for various machine learning and deep learning tasks. Models that can learn from such inputs are essential for working with graph data effectively. This paper identifies nodes and edges within specific applications, such as text, entities, and relations, to create graph structures. Different applications may require various graph neural network (GNN) models. GNNs facilitate the exchange of information between nodes in a graph, enabling them to understand dependencies within the nodes and edges. The paper delves into specific GNN models like graph convolution networks (GCNs), GraphSAGE, and graph attention networks (GATs), which are widely used in various applications today. It also discusses the message-passing mechanism employed by GNN models and examines the strengths and limitations of these models in different domains. Furthermore, the paper explores the diverse applications of GNNs, the datasets commonly used with them, and the Python libraries that support GNN models. It offers an extensive overview of the landscape of GNN research and its practical implementations.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2196-1115
2196-1115
DOI:10.1186/s40537-023-00876-4