Graph Neural Networks: A Review of Methods and Applications

By Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Maosong Sun. 2018

7,152 citations recorded by the source corpus.

Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics system, learning molecular fingerprints, predicting protein interface, and classifying diseases require a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures, like the dependency tree of sentences and the scene graph of images, is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are connectionist models that capture the dependence of graphs via message passing between the nodes of graphs. Unlike standard neural networks, graph neural networks retain a state that can represent information from its neighborhood with arbitrary depth. Although the primitive GNNs have been found difficult to train for a fixed point, recent advances in network architectures, optimization techniques, and parallel computation have enabled successful learning with them. In recent years, systems based on variants of graph neural networks such as graph convolutional network (GCN), graph attention network (GAT), gated graph neural network (GGNN) have demonstrated ground-breaking performance on many tasks mentioned above. In this survey, we provide a detailed review over existing graph neural network models, systematically categorize the applications, and propose four open problems for future research.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019, background): “However, the adjacency matrix can be difficult for the neural network to interpret (Zhou et al. 2018), since the features are highly dependent on one another.”
Lifelong Graph Learning (2020, methodology): “Graph neural networks have been widely used to solve problems with graph-structured data [59].”
Simplifying Graph Convolutional Networks (2019, background): “We refer to Zhou et al. (2018); Battaglia et al. (2018); Wu et al. (2019) for a more comprehensive review.”
Graph Neural Network for Traffic Forecasting: A Survey (2021, background): “For a wider and deeper discussion of graph neural networks, the readers may refer to recent surveys [2], [229], [230].”
Graph Neural Networks in Network Neuroscience (2021, background): “GNNs,we kindly refer the reader to [42], [43], [44], [46].”
A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions (2024, methodology): “Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs [30].”
A Survey on Oversmoothing in Graph Neural Networks (2023, background): “…et al. (2018), transportation Derrow-Pinion et al. (2021), computational chemistry (Gilmer et al., 2017), drug discovery Gaudelet et al. (2021), particle physics (Shlomi et al., 2020), and analysis of social networks (see Zhou et al. (2019); Bronstein et al. (2021) for additional applications).”
Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer (2021, methodology): “Our work is also related to the variants of Graph Neural Networks (GNN) (Kipf and Welling, 2016; Veliˇckovi´c et al., 2017; Zhou et al., 2018), especially Graph Transformers (Yun et al., 2019; Chen et al., 2019; Hu et al., 2020; Wang et al., 2020b).”
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “as Multi-Agent Deep Reinforcement Learning [288]–[290], Graph Neural Networks (GNNs) [291], [292], can also be exploited to facilitate this process.”
CoCoGUM: Contextual Code Summarization with Multi-Relational GNN on UMLs (2020, background): “The attempt to extend deep neural networks to graph data has spawned Graph Neural Networks (GNNs) [28, 30].”
Artificial Neural Networks and Machine Learning – ICANN 2021: 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part III (2021, background): “Other applications arise in the context of social and biological networks, knowledge graphs, e-commerce, among others [48,44].”
scDeepSort: a pre-trained cell-type annotation method for single-cell transcriptomics using deep learning with a weighted graph neural network (2021, background): “Unlike standard neural networks, GNNs retain a state that represents information from its neighborhood with arbitrary depth, which has demonstrated ground-breaking performance on many learning tasks (27).”
Amalgamating Knowledge from Heterogeneous Graph Neural Networks (2021, background): “Graph neural networks (GNNs) have achieved unprecedented advances in recent years, showing promising performance in handling graph data lying in the non-Euclidean domain [16, 37, 53, 44, 6, 41, 19, 23, 36, 13, 18, 25, 42].”
Towards Deeper Graph Neural Networks with Differentiable Group Normalization (2020, result): “This observation contradicts with the common belief that GNN models work best with a few layers on current benchmark datasets [34].”
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning (2020, background): “Graph Neural Networks (GNN) [34] are a family of deep neural networks that can learn representation of graph-structured (non-euclidean) data, which has many applications in real life [35, 36].”
Discrete Graph Structure Learning for Forecasting Multiple Time Series (2021, background): “Graph neural networks (Zhang et al., 2018; Zhou et al., 2018; Wu et al., 2019) emerged quickly in deep learning to handle graph-structured data.”