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 (19)

• Semi-Supervised Classification with Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Variational Graph Auto-Encoders
• Deep Graph Contrastive Representation Learning
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Graph-Bert: Only Attention is Needed for Learning Graph Representations
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Structure-Feature based Graph Self-adaptive Pooling
• Active Learning for Graph Embedding
• Attributed Graph Clustering via Adaptive Graph Convolution
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
• Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
• Contrastive Self-supervised Learning for Graph Classification
• Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders
• Deep Contextual Learners for Protein Networks