A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions
Abstract 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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-01-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40537-023-00876-4 |
| _version_ | 1797349828262363136 |
|---|---|
| author | Bharti Khemani Shruti Patil Ketan Kotecha Sudeep Tanwar |
| author_facet | Bharti Khemani Shruti Patil Ketan Kotecha Sudeep Tanwar |
| author_sort | Bharti Khemani |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-08T12:36:06Z |
| format | Article |
| id | doaj.art-0ec98f5313ea4605b8859ecb62415bc9 |
| institution | Directory Open Access Journal |
| issn | 2196-1115 |
| language | English |
| last_indexed | 2024-03-08T12:36:06Z |
| publishDate | 2024-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj.art-0ec98f5313ea4605b8859ecb62415bc92024-01-21T12:24:30ZengSpringerOpenJournal of Big Data2196-11152024-01-0111114310.1186/s40537-023-00876-4A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directionsBharti Khemani0Shruti Patil1Ketan Kotecha2Sudeep Tanwar3Symbiosis Institute of Technology Pune Campus, Symbiosis International (Deemed University) (SIU)Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis Institute of Technology Pune Campus, Symbiosis International (Deemed University) (SIU)Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis Institute of Technology Pune Campus, Symbiosis International (Deemed University) (SIU)IEEE, Department of Computer Science and Engineering, Institute of Technology, Nirma UniversityAbstract 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.https://doi.org/10.1186/s40537-023-00876-4Graph Neural Network (GNN)Graph Convolution Network (GCN)GraphSAGEGraph Attention Networks (GAT)Message Passing MechanismNatural Language Processing (NLP) |
| spellingShingle | Bharti Khemani Shruti Patil Ketan Kotecha Sudeep Tanwar A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions Journal of Big Data Graph Neural Network (GNN) Graph Convolution Network (GCN) GraphSAGE Graph Attention Networks (GAT) Message Passing Mechanism Natural Language Processing (NLP) |
| title | A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions |
| title_full | A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions |
| title_fullStr | A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions |
| title_full_unstemmed | A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions |
| title_short | A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions |
| title_sort | review of graph neural networks concepts architectures techniques challenges datasets applications and future directions |
| topic | Graph Neural Network (GNN) Graph Convolution Network (GCN) GraphSAGE Graph Attention Networks (GAT) Message Passing Mechanism Natural Language Processing (NLP) |
| url | https://doi.org/10.1186/s40537-023-00876-4 |
| work_keys_str_mv | AT bhartikhemani areviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT shrutipatil areviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT ketankotecha areviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT sudeeptanwar areviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT bhartikhemani reviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT shrutipatil reviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT ketankotecha reviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections AT sudeeptanwar reviewofgraphneuralnetworksconceptsarchitecturestechniqueschallengesdatasetsapplicationsandfuturedirections |