dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning

Abstract

Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need of capturing dynamics for prediction on a toy data set created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real world data sets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction.

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Deep Convolutional Networks on Graph-Structured Data
• Variational Graph Auto-Encoders
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorization
• DyLink2Vec: Effective Feature Representation for Link Prediction in Dynamic Networks
• TIMERS: Error-Bounded SVD Restart on Dynamic Networks

Cited by in corpus (51)

• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Representation Learning for Dynamic Graphs: A Survey
• Anomaly Detection in Dynamic Graphs: A Comprehensive Survey
• Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
• CGC: Contrastive Graph Clustering for Community Detection and Tracking
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• A Spatial-Temporal Graph Neural Network Framework for Automated Software Bug Triaging
• Deep learning for dynamic graphs: models and benchmarks
• Approximating Network Centrality Measures Using Node Embedding and Machine Learning
• Meta-Inductive Node Classification across Graphs
• Deep Collaborative Embedding for information cascade prediction
• Network representation learning systematic review: ancestors and current development state
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• CLDG: Contrastive Learning on Dynamic Graphs
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
• ExEm: Expert Embedding using dominating set theory with deep learning approaches
• Understanding graph embedding methods and their applications
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
• On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• Link prediction in dynamic networks using random dot product graphs
• GraphKKE: Graph Kernel Koopman Embedding for Human Microbiome Analysis
• RoleSeer: Understanding Informal Social Role Changes in MMORPGs via Visual Analytics
• DyANE: Dynamics-aware node embedding for temporal networks
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey
• Networks of Power: Analyzing World Leaders Interactions on Social Media
• DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability
• GRADE: Graph Dynamic Embedding
• Dynamic Link Prediction Using Graph Representation Learning with Enhanced Structure and Temporal Information
• Learning to Evolve on Dynamic Graphs
• ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
• STEC-Net: A Spatiotemporal Graph Neural Framework for Community Discovery in Dynamic Social Networks
• From Static to Dynamic Node Embeddings
• TSAM: Temporal Link Prediction in Directed Networks based on Self-Attention Mechanism
• Graph-Level Embedding for Time-Evolving Graphs
• EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
• DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums
• Robust Dynamic Network Embedding via Ensembles
• SPAN: Subgraph Prediction Attention Network for Dynamic Graphs
• Divide and Rule: Recurrent Partitioned Network for Dynamic Processes
• DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks
• Multi-View Dynamic Heterogeneous Information Network Embedding
• A Local Similarity-Preserving Framework for Nonlinear Dimensionality Reduction with Neural Networks
• FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding
• Embedding Dynamic Attributed Networks by Modeling the Evolution Processes