Representation Learning for Dynamic Graphs: A Survey
It provides a comprehensive overview for researchers and practitioners working with dynamic graph data, but it is incremental as it synthesizes existing work without introducing new methods.
This survey reviews recent advances in representation learning for dynamic graphs, addressing the challenge of modeling evolving nodes, attributes, and edges in applications like social networks and biology, and categorizes existing models from an encoder-decoder perspective.
Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance. Traditionally, machine learning models for graphs have been mostly designed for static graphs. However, many applications involve evolving graphs. This introduces important challenges for learning and inference since nodes, attributes, and edges change over time. In this survey, we review the recent advances in representation learning for dynamic graphs, including dynamic knowledge graphs. We describe existing models from an encoder-decoder perspective, categorize these encoders and decoders based on the techniques they employ, and analyze the approaches in each category. We also review several prominent applications and widely used datasets and highlight directions for future research.