Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey

Abstract

Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems, and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. To address the challenges resulting from the fact that this research crosses diverse fields as well as to survey dynamic graph neural networks, this work is split into two main parts. First, to address the ambiguity of the dynamic network terminology we establish a foundation of dynamic networks with consistent, detailed terminology and notation. Second, we present a comprehensive survey of dynamic graph neural network models using the proposed terminology

28 pages, 9 figures, 8 tables

References in corpus (30)

• A Comprehensive Survey on Graph Neural Networks
• WaveNet: A Generative Model for Raw Audio
• The structure and dynamics of multilayer networks
• Graph Neural Networks: A Review of Methods and Applications
• Variational Graph Auto-Encoders
• Activity driven modeling of time varying networks
• Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks
• Evaluating Link Prediction Methods
• Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
• Dynamic stochastic blockmodels for time-evolving social networks
• Deep Learning on Graphs: A Survey
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• Time2Vec: Learning a Vector Representation of Time
• A Relational Event Approach to Modeling Behavioral Dynamics
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• Self-attention with Functional Time Representation Learning
• Tempus Volat, Hora Fugit -- A Survey of Tie-Oriented Dynamic Network Models in Discrete and Continuous Time
• Variational Graph Recurrent Neural Networks
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
• A Survey on Dynamic Network Embedding
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• DynamicGEM: A Library for Dynamic Graph Embedding Methods
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
• Generative Graph Convolutional Network for Growing Graphs
• A Heterogeneous Dynamical Graph Neural Networks Approach to Quantify Scientific Impact
• Simulation and Augmentation of Social Networks for Building Deep Learning Models
• Revealing evolutions in dynamical networks
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs

Cited by in corpus (27)

• Gated Graph Recurrent Neural Networks
• Deep learning of contagion dynamics on complex networks
• Graph Neural Networks for Text Classification: A Survey
• Anomaly Detection in Dynamic Graphs: A Comprehensive Survey
• Graph Deep Learning for Time Series Forecasting
• A Network Science perspective of Graph Convolutional Networks: A survey
• Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation
• MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline
• On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• Graph Reinforcement Learning for Power Grids: A Comprehensive Survey
• Financial Crime & Fraud Detection Using Graph Computing: Application Considerations & Outlook
• INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks
• Deep Structural Point Process for Learning Temporal Interaction Networks
• Learning to Evolve on Dynamic Graphs
• ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
• Graph Computing for Financial Crime and Fraud Detection: Trends, Challenges and Outlook
• Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism
• Focus Where It Matters: Graph Selective State Focused Attention Networks
• Geometric learning of the conformational dynamics of molecules using dynamic graph neural networks
• A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems
• Making the complete OpenAIRE citation graph easily accessible through compact data representation
• Understanding the Dynamics of DNNs Using Graph Modularity
• Event Detection on Dynamic Graphs
• Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks
• A Literature Review of Recent Graph Embedding Techniques for Biomedical Data
• Spectral Transform Forms Scalable Transformer