Dynamic Graph Convolutional Networks

Abstract

Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly exploit structured data and temporal information through the use of a neural network model. To the best of our knowledge, this task has not been addressed using these kind of architectures. For this reason, we propose two novel approaches, which combine Long Short-Term Memory networks and Graph Convolutional Networks to learn long short-term dependencies together with graph structure. The quality of our methods is confirmed by the promising results achieved.

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Automated Pruning for Deep Neural Network Compression
• Temporal Dynamic Graph LSTM for Action-driven Video Object Detection

Cited by in corpus (53)

• Graph Neural Networks: A Review of Methods and Applications
• Graph Learning: A Survey
• Learning to Simulate Complex Physics with Graph Networks
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Current and future directions in network biology
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
• Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• Representation Learning for Dynamic Graphs: A Survey
• Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
• A Survey of Adversarial Learning on Graphs
• Multiple-Human Parsing in the Wild
• Entropic Dynamic Time Warping Kernels for Co-evolving Financial Time Series Analysis
• Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
• Efficient Scaling of Dynamic Graph Neural Networks
• Dynamic Graph Convolutional Networks Using the Tensor M-Product
• AutoGraph: Automated Graph Neural Network
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• Graph Convolution: A High-Order and Adaptive Approach
• Federated Dynamic GNN with Secure Aggregation
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
• Network Alignment
• Action Sequence Augmentation for Early Graph-based Anomaly Detection
• PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series
• Deep Graph Similarity Learning: A Survey
• Temporal Graph Signal Decomposition
• On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
• A Heterogeneous Dynamical Graph Neural Networks Approach to Quantify Scientific Impact
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
• Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer
• Learning to Evolve on Dynamic Graphs
• Deep learning reveals hidden interactions in complex systems
• Improved supervised prediction of aging-related genes via weighted dynamic network analysis
• Learning Representation over Dynamic Graph using Aggregation-Diffusion Mechanism
• Learning Attribute-Structure Co-Evolutions in Dynamic Graphs
• Streaming Network Embedding through Local Actions
• Temporal Graph Network Embedding with Causal Anonymous Walks Representations
• Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
• Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement
• Spectral Transform Forms Scalable Transformer
• Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning
• Deep graph learning for semi-supervised classification
• RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks
• TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation