Representation Learning over Dynamic Graphs
arXiv:1803.04051
Abstract
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.
References in corpus (10)
- Inductive Representation Learning on Large Graphs
- Variational Graph Auto-Encoders
- Discriminative Embeddings of Latent Variable Models for Structured Data
- Representation Learning on Graphs: Methods and Applications
- DynGEM: Deep Embedding Method for Dynamic Graphs
- Dynamic Word Embeddings
- Fake News Mitigation via Point Process Based Intervention
- Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
- Dynamics on networks: competition of temporal and topological correlations
- Graph Clustering with Dynamic Embedding
Cited by in corpus (12)
- Node Embedding over Temporal Graphs
- Inductive Representation Learning on Temporal Graphs
- Learning Dynamic Embeddings from Temporal Interactions
- Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution
- Graph Ordering: Towards the Optimal by Learning
- Representing Social Networks as Dynamic Heterogeneous Graphs
- Temporal Network Embedding with Micro- and Macro-dynamics
- DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums
- Dynamic Graph Embedding via LSTM History Tracking
- Dynamic Embedding on Textual Networks via a Gaussian Process
- Dynamic Joint Variational Graph Autoencoders
- Multi-View Dynamic Heterogeneous Information Network Embedding