Deep Learning on Graphs: A Survey

By Ziwei Zhang, Peng Cui, Wenwu Zhu. IEEE Transactions on Knowledge and Data Engineering, 2018

1,598 citations recorded by the source corpus.

Deep learning has been shown to be successful in a number of domains, ranging from acoustics, images, to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics of graphs. Recently, substantial research efforts have been devoted to applying deep learning methods to graphs, resulting in beneficial advances in graph analysis techniques. In this survey, we comprehensively review the different types of deep learning methods on graphs. We divide the existing methods into five categories based on their model architectures and training strategies: graph recurrent neural networks, graph convolutional networks, graph autoencoders, graph reinforcement learning, and graph adversarial methods. We then provide a comprehensive overview of these methods in a systematic manner mainly by following their development history. We also analyze the differences and compositions of different methods. Finally, we briefly outline the applications in which they have been used and discuss potential future research directions.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/30b38ca8151bbd5a5ff45bce94297d1248ff58b5

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

1. Xiangnan He
2. Bryan Perozzi
3. Xiang Wang
4. Chuan Shi
5. Shirui Pan
6. Tat-seng Chua
7. Meng Wang
8. Christopher R'e

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yi Yang
3. Luc Van Gool
4. Meng Wang
5. Philip H. S. Torr
6. Xiangnan He
7. Chunhua Shen
8. Song Bai

In Statistical and Nonlinear Physics

1. Bryan Perozzi
2. Shirui Pan
3. Huan Liu
4. Michael M. Bronstein
5. Xiao Wang
6. Xingquan Zhu
7. Chuan Shi
8. Wenwu Zhu

Citations in the corpus

• Implicit Graph Neural Networks (2020, methodology): “Graph neural networks (GNNs) (Zhou et al., 2018; Zhang et al., 2020) have been widely used on graph-structured data to obtain a meaningful representation of nodes in the graph.”
• Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “Zhang et al. [15] reviewed different deep learning methods on graphs and identified two new classes of models not addressed in previous surveys: graph reinforcement learning (Graph RL) models, and graph adversarial methods.”
• Data Augmentation for Graph Neural Networks (2020, background): “…and Leskovec 2017; Kipf and Welling 2016a; Veličković et al. 2017; Xu et al. 2018a; Zhang et al. 2019a; Chen, Ma, and Xiao 2018; Wu et al. 2019; Zhang, Cui, and Zhu 2018; Xu et al. 2018b) have emerged as a rising approach for datadriven inference on graphs, achieving promising results…”
• Contrastive Multi-View Representation Learning on Graphs (2020, neutral): “For an overview see (Zhang et al., 2020; Wu et al., 2020).”
• A Gentle Introduction to Deep Learning for Graphs (2019, background): “he assessment of deep learning models for graphs [108, 34], which calls for a more principled approach to the topic. Lastly, a certain number of survey papers have started to appear in the literature [7, 19, 48, 55, 144, 130, 143], while a more slowly-paced introduction to the methodology seems lack”
• Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions (2023, background): “5 of 26 Unfortunately, there is occasionally an absence of data for the direct use of DL [23,24]. model.”
• Boosting Visual Question Answering with Context-aware Knowledge Aggregation (2020, methodology): “Inspired by recent works on graph neural networks [30] and knowledge-based question answering [29], we utilize a particular type of graph convolution network to aggregate graph knowledge into anchor entities according to a specific contextual query.”
• HyGCN: A GCN Accelerator with Hybrid Architecture (2020, methodology): “GCNs follow a neighborhood aggregation scheme, where the feature vector of each vertex is computed by recursively aggregating and transforming the representation vectors of its neighbor vertices [18,39,47].”
• Graph convolutional networks for computational drug development and discovery (2019, background): “However, applying deep learning to the these graph data is non-trivial because of the unique characteristics of graphs [15].”
• Graph Neural Networks in Network Neuroscience (2021, methodology): “For instance, [42], [43], [44], [46], [47]”
• SIGN: Scalable Inception Graph Neural Networks (2020, background): “Deep learning on graphs, also known as geometric deep learning (GDL) or graph representation learning (GRL), has emerged in a matter of just a few years from a niche topic to one of the most prominent fields in machine learning.”
• Evolutionary Architecture Search for Graph Neural Networks (2020, background): “As of today, many GNN structures with diverse learning mechanisms have been proposed for node relationship modeling [8], [9].”
• Graph Representation Learning in Biomedicine and Healthcare (2021, neutral): “However, hand-crafting optimally predictive features across diverse types of networks and applications can be challenging 18 .”
• 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.”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “sented as an attributed user-item bipartite graph or a heterogeneous information network [151], [262], and knowledge enhanced recommendation is defined as a combination of”