Graph Neural Networks: Methods, Applications, and Opportunities

Abstract

In the last decade or so, we have witnessed deep learning reinvigorating the machine learning field. It has solved many problems in the domains of computer vision, speech recognition, natural language processing, and various other tasks with state-of-the-art performance. The data is generally represented in the Euclidean space in these domains. Various other domains conform to non-Euclidean space, for which graph is an ideal representation. Graphs are suitable for representing the dependencies and interrelationships between various entities. Traditionally, handcrafted features for graphs are incapable of providing the necessary inference for various tasks from this complex data representation. Recently, there is an emergence of employing various advances in deep learning to graph data-based tasks. This article provides a comprehensive survey of graph neural networks (GNNs) in each learning setting: supervised, unsupervised, semi-supervised, and self-supervised learning. Taxonomy of each graph based learning setting is provided with logical divisions of methods falling in the given learning setting. The approaches for each learning task are analyzed from both theoretical as well as empirical standpoints. Further, we provide general architecture guidelines for building GNNs. Various applications and benchmark datasets are also provided, along with open challenges still plaguing the general applicability of GNNs.

Submitted to ACM

References in corpus (55)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• The diameter of the world wide web
• Neural Message Passing for Quantum Chemistry
• The Dynamics of Viral Marketing
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Graph Contrastive Learning with Adaptive Augmentation
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Variational Graph Auto-Encoders
• Pitfalls of Graph Neural Network Evaluation
• DeepInf: Social Influence Prediction with Deep Learning
• Graph Self-Supervised Learning: A Survey
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Learning Deep Generative Models of Graphs
• Self-Supervised Graph Transformer on Large-Scale Molecular Data
• Deep Graph Contrastive Representation Learning
• Learning Graph Embedding with Adversarial Training Methods
• Community Interaction and Conflict on the Web
• Representation Learning on Graphs: Methods and Applications
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Benchmarking Graph Neural Networks
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
• Design Space for Graph Neural Networks
• Graph-Bert: Only Attention is Needed for Learning Graph Representations
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Invariant and Equivariant Graph Networks
• A Survey on The Expressive Power of Graph Neural Networks
• Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Structure-Feature based Graph Self-adaptive Pooling
• Understanding Attention and Generalization in Graph Neural Networks
• ktrain: A Low-Code Library for Augmented Machine Learning
• Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
• Active Learning for Graph Embedding
• On the equivalence between graph isomorphism testing and function approximation with GNNs
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Graph Policy Network for Transferable Active Learning on Graphs
• Attributed Graph Clustering via Adaptive Graph Convolution
• What graph neural networks cannot learn: depth vs width
• Automated Self-Supervised Learning for Graphs
• Graph Nets for Partial Charge Prediction
• AutoGL: A Library for Automated Graph Learning
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
• Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
• Iterative Graph Self-Distillation
• Contrastive Self-supervised Learning for Graph Classification
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction
• Deep Contextual Learners for Protein Networks
• Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders