Graph Neural Networks: A Review of Methods and Applications (2018-12-20T00:00:00.000000Z)

TL;DR

A detailed review over existing graph neural network models is provided, systematically categorize the applications, and four open problems for future research are proposed.

Authors

Zhiyuan Liu

34 papers

Maosong Sun

46 papers

Jie Zhou

14 papers

Ganqu Cui

5 papers

Cheng Yang

4 papers

Zhengyan Zhang

3 papers

TL;DR

Authors

References302 items

Design Space for Graph Neural Networks

Graph Embedding for Combinatorial Optimization: A Survey

Modeling Complex Spatial Patterns with Temporal Features via Heterogenous Graph Embedding Networks

Adaptive Graph Encoder for Attributed Graph Embedding

Scaling Graph Neural Networks with Approximate PageRank

F-HMTC: Detecting Financial Events for Investment Decisions Based on Neural Hierarchical Multi-Label Text Classification

GPT-GNN: Generative Pre-Training of Graph Neural Networks

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

Graph Policy Network for Transferable Active Learning on Graphs

Contrastive Multi-View Representation Learning on Graphs

Graphon Neural Networks and the Transferability of Graph Neural Networks

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

Deep Lagrangian Constraint-based Propagation in Graph Neural Networks

Open Graph Benchmark: Datasets for Machine Learning on Graphs

SIGN: Scalable Inception Graph Neural Networks

Graph Convolutional Networks with Markov Random Field Reasoning for Social Spammer Detection

Heterogeneous Network Representation Learning: Survey, Benchmark, Evaluation, and Beyond

A Survey of Adversarial Learning on Graphs

Heterogeneous Graph Transformer

Unifying Graph Convolutional Neural Networks and Label Propagation

Generalization and Representational Limits of Graph Neural Networks

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Graph-Bert: Only Attention is Needed for Learning Graph Representations

A Fair Comparison of Graph Neural Networks for Graph Classification

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

GMAN: A Graph Multi-Attention Network for Traffic Prediction

Graph convolutional networks: a comprehensive review

Graph Transformer Networks

Using External Knowledge for Financial Event Prediction Based on Graph Neural Networks

Fine-grained Fact Verification with Kernel Graph Attention Network

Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis

Reasoning Over Semantic-Level Graph for Fact Checking

Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View

Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs

Learning Sparse Nonparametric DAGs

Neural Dynamics on Complex Networks

HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction

Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

Transferability of Spectral Graph Convolutional Neural Networks

OAG: Toward Linking Large-scale Heterogeneous Entity Graphs

Heterogeneous Graph Neural Network

Robust Graph Convolutional Networks Against Adversarial Attacks

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting

Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology

GraphSAINT: Graph Sampling Based Inductive Learning Method

What graph neural networks cannot learn: depth vs width

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Attributed Graph Clustering via Adaptive Graph Convolution

Strategies for Pre-training Graph Neural Networks

On the equivalence between graph isomorphism testing and function approximation with GNNs

Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

Revisiting Graph Neural Networks: All We Have is Low-Pass Filters

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

Dynamically Fused Graph Network for Multi-hop Reasoning

Cognitive Graph for Multi-Hop Reading Comprehension at Scale

Universal Invariant and Equivariant Graph Neural Networks

Graph U-Nets

Stability and Generalization of Graph Convolutional Neural Networks

Approximation Ratios of Graph Neural Networks for Combinatorial Problems

Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Explainability Techniques for Graph Convolutional Networks

Understanding Attention and Generalization in Graph Neural Networks

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

Graph Normalizing Flows

Graph Convolutional Networks with EigenPooling

Graph Matching Networks for Learning the Similarity of Graph Structured Objects

Self-Attention Graph Pooling

Graph Wavelet Neural Network

DeepGCNs: Can GCNs Go As Deep As CNNs?

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

Heterogeneous Graph Attention Network

Fast Graph Representation Learning with PyTorch Geometric

GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding