A Comprehensive Survey on Graph Neural Networks
Всеобъемлющий обзор графовых нейронных сетей
2020-03-24
SCID: 54.1/hfsk7d2w
Discuss with AI
convolutional GNNsgraph autoencodersgraph neural networks (GNNs)recurrent GNNsspatial-temporal GNNs
Figures from the paper
Abstract (AI)
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.
Key Findings
1
Graph neural networks (GNNs) extend deep learning to non-Euclidean graph-structured data with complex relationships and interdependencies.
2
The article identifies challenges of applying existing machine learning algorithms to graph data and proposes potential future research directions in GNNs.
3
The paper proposes a new taxonomy categorizing state-of-the-art GNNs into four groups: recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs.
4
The survey summarizes GNN applications across various domains and compiles open-source code, benchmark datasets, and model evaluation practices.
Research Object
Graph neural networks (GNNs)
Research Subject
Comprehensive overview, taxonomy, applications, benchmarks, code resources, model evaluation, and research directions for GNNs (including recurrent, convolutional, graph autoencoders, and spatial-temporal variants)
Publication Details
Publication Date
2020-03-24
Journal
Publisher
ISSN
Cited by
12452
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai18
Deep Residual Learning for Image Recognition2016
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
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
The Graph Neural Network Model2008
Effective Approaches to Attention-based Neural Machine Translation2015
Dynamic Graph CNN for Learning on Point Clouds2019
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation2016
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
Neural Message Passing for Quantum Chemistry2017
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules2018
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting2019
Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
Collective Classification in Network Data2008
Heterogeneous Graph Attention Network2019
Quantum chemistry structures and properties of 134 kilo molecules2014
Discrete Signal Processing on Graphs2013
Cited by20
Graph neural networks: A review of methods and applications2020
Deep Learning for Generic Object Detection: A Survey2019
ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope2023
Knowledge Graphs2021
Graph convolutional networks: a comprehensive review2019
Deep Learning on Graphs: A Survey2020
Graph Neural Networks in Recommender Systems: A Survey2022
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions2023
Traffic Flow Prediction via Spatial Temporal Graph Neural Network2020
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection2024
Machine Learning Methods for Small Data Challenges in Molecular Science2023
Graph Neural Networks for Intelligent Transportation Systems: A Survey2023
A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications2024
Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey2021
Computing Graph Neural Networks: A Survey from Algorithms to Accelerators2021
A review of large language models and autonomous agents in chemistry2024
End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection2021
A Survey on Graph Representation Learning Methods2023
Neural networks to learn protein sequence–function relationships from deep mutational scanning data2021
Financial Cybercrime: A Comprehensive Survey of Deep Learning Approaches to Tackle the Evolving Financial Crime Landscape2021