Graph neural networks: A review of methods and applications
Графовые нейронные сети: обзор методов и приложений
2020-01-01
SCID: 54.1/3brjuufe
Discuss with AI
graph attention network (GAT)graph convolutional network (GCN)graph neural networksgraph recurrent network (GRN)message passing
Figures from the paper
Abstract (AI)
Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.
Key Findings
1
GNNs are applicable both to inherently structured domains (physics systems, molecular fingerprints, protein interface prediction, disease classification) and to extracted-structure tasks from non-structural data (text dependency trees, image scene graphs).
2
Graph neural networks (GNNs) model graph-structured data by capturing dependencies via message passing between nodes.
3
The paper systematically categorizes GNN applications and identifies four open problems for future research.
4
The survey proposes a general design pipeline for GNN models and discusses variant choices for each component of that pipeline.
5
Variants of GNNs—graph convolutional networks (GCN), graph attention networks (GAT), and graph recurrent networks (GRN)—have achieved ground-breaking performance on many deep learning tasks.
Research Object
Graph neural networks (GNNs)
Research Subject
Methods, design components, variants, and applications of GNNs including message-passing architectures (e.g., GCN, GAT, GRN) and categorization of their use-cases and open research problems
Publication Details
Publication Date
2020-01-01
Journal
Publisher
ISSN
Cited by
7812
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
Deep Residual Learning for Image Recognition2016
ImageNet classification with deep convolutional neural networks2017
Gradient-based learning applied to document recognition1998
Semi-Supervised Classification with Graph Convolutional Networks2016
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
Neural Machine Translation by Jointly Learning to Align and Translate2014
A Comprehensive Survey on Graph Neural Networks2020
Non-local Neural Networks2018
The Graph Neural Network Model2008
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
Dynamic Graph CNN for Learning on Point Clouds2019
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
Neural Message Passing for Quantum Chemistry2017
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting2019
Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
Heterogeneous Graph Attention Network2019
Convolutional 2D Knowledge Graph Embeddings2018
Heterogeneous Graph Transformer2020
Graph convolutional networks: a comprehensive review2019
Deep Learning on Graphs: A Survey2020
Cited by20
Deep Learning for Generic Object Detection: A Survey2019
A review of uncertainty quantification in deep learning: Techniques, applications and challenges2021
Graph convolutional networks: a comprehensive review2019
Deep Learning on Graphs: A Survey2020
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey2020
Graph Neural Networks in Recommender Systems: A Survey2022
Deep learning in optical metrology: a review2022
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions2023
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT2021
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey2023
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges2022
Graph Neural Networks and Their Current Applications in Bioinformatics2021
Graph Neural Networks for Intelligent Transportation Systems: A Survey2023
Machine learning and deep learning based predictive quality in manufacturing: a systematic review2022
Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey2021
Computing Graph Neural Networks: A Survey from Algorithms to Accelerators2021
A Survey on Graph Representation Learning Methods2023
Financial Cybercrime: A Comprehensive Survey of Deep Learning Approaches to Tackle the Evolving Financial Crime Landscape2021
Anomaly Detection in Dynamic Graphs: A Comprehensive Survey2024
A Survey on Malware Detection with Graph Representation Learning2024