Graph Neural Networks: Taxonomy, Advances and Trends

Abstract

Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks. Up to now, there have been several surveys on this topic. However, they usually lay emphasis on different angles so that the readers can not see a panorama of the graph neural networks. This survey aims to overcome this limitation, and provide a comprehensive review on the graph neural networks. First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 400 relevant literatures to show the panorama of the graph neural networks. All of them are classified into the corresponding categories. In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the facing challenges. It is expected that more and more scholars can understand and exploit the graph neural networks, and use them in their research community.

arXiv comment55 pages, 7 figures

References in corpus (115)

• A Comprehensive Survey on Graph Neural Networks
• DeepWalk: Online Learning of Social Representations
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Variational Inference: A Review for Statisticians
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• KGAT: Knowledge Graph Attention Network for Recommendation
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Multi-Scale Context Aggregation by Dilated Convolutions
• Pre-trained Models for Natural Language Processing: A Survey
• Session-based Recommendation with Graph Neural Networks
• Modeling polypharmacy side effects with graph convolutional networks
• Graph Neural Networks: A Review of Methods and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Graph Contrastive Learning with Adaptive Augmentation
• Adversarial Attacks on Neural Networks for Graph Data
• Recurrent Models of Visual Attention
• Representation Learning on Graphs with Jumping Knowledge Networks
• Variational Graph Auto-Encoders
• Learning Convolutional Neural Networks for Graphs
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Pitfalls of Graph Neural Network Evaluation
• Interaction Networks for Learning about Objects, Relations and Physics
• DeepInf: Social Influence Prediction with Deep Learning
• Towards Deeper Graph Neural Networks
• Graph Transformer Networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Large-Scale Learnable Graph Convolutional Networks
• MolGAN: An implicit generative model for small molecular graphs
• Dynamic Graph Convolutional Networks
• Learning Deep Generative Models of Graphs
• Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• A Gentle Introduction to Deep Learning for Graphs
• Adversarial Attack and Defense on Graph Data: A Survey
• DynGEM: Deep Embedding Method for Dynamic Graphs
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case
• Attention-based Graph Neural Network for Semi-supervised Learning
• Residual Gated Graph ConvNets
• Topology Adaptive Graph Convolutional Networks
• PairNorm: Tackling Oversmoothing in GNNs
• Benchmarking Graph Neural Networks
• Adaptive Sampling Towards Fast Graph Representation Learning
• Towards Sparse Hierarchical Graph Classifiers
• Attention, Learn to Solve Routing Problems!
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Strategies for Pre-training Graph Neural Networks
• Deep Learning on Graphs: A Survey
• GMNN: Graph Markov Neural Networks
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Graph-Bert: Only Attention is Needed for Learning Graph Representations
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Universal Invariant and Equivariant Graph Neural Networks
• Relational Graph Attention Networks
• Geom-GCN: Geometric Graph Convolutional Networks
• Deep Network Embedding for Graph Representation Learning in Signed Networks
• Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data
• Certifiable Robustness and Robust Training for Graph Convolutional Networks
• Invariant and Equivariant Graph Networks
• What Can Neural Networks Reason About?
• Graph Capsule Convolutional Neural Networks
• Position-aware Graph Neural Networks
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• Covariant Compositional Networks For Learning Graphs
• A Survey on The Expressive Power of Graph Neural Networks
• Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
• Graph Wavelet Neural Network
• A Generalization of Convolutional Neural Networks to Graph-Structured Data
• Structural Deep Embedding for Hyper-Networks
• Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
• GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
• Edge Attention-based Multi-Relational Graph Convolutional Networks
• Graph Convolutional Neural Networks via Scattering
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• Graph Kernels: State-of-the-Art and Future Challenges
• Explainability Techniques for Graph Convolutional Networks
• M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
• Signed Graph Convolutional Network
• Generalization and Representational Limits of Graph Neural Networks
• Certifiable Robustness to Graph Perturbations
• Graph Partition Neural Networks for Semi-Supervised Classification
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• HNHN: Hypergraph Networks with Hyperedge Neurons
• Batch Virtual Adversarial Training for Graph Convolutional Networks
• LambdaNet: Probabilistic Type Inference using Graph Neural Networks
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• Joint embedding of structure and features via graph convolutional networks
• Variational Graph Recurrent Neural Networks
• Heterogeneous Graph Transformer
• CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Streaming Graph Neural Networks
• Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations
• G2SAT: Learning to Generate SAT Formulas
• Motif-Driven Contrastive Learning of Graph Representations
• Deep Learning for Learning Graph Representations
• Multi-dimensional Graph Convolutional Networks
• Memory-Based Graph Networks
• Towards Efficient Large-Scale Graph Neural Network Computing
• Tensor graph convolutional neural network
• PiNet: A Permutation Invariant Graph Neural Network for Graph Classification
• Spectral Pyramid Graph Attention Network for Hyperspectral Image Classification
• Learning Graph-Level Representations with Recurrent Neural Networks
• Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
• Inferring Javascript types using Graph Neural Networks
• Variational Recurrent Neural Networks for Graph Classification
• Topology and Prediction Focused Research on Graph Convolutional Neural Networks

Cited by in corpus (1)

• Node Feature Kernels Increase Graph Convolutional Network Robustness