Representation Learning for Dynamic Graphs: A Survey

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. Th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-04
Main Authors: Seyed Mehran Kazemi, Goel, Rishab, Jain, Kshitij, Kobyzev, Ivan, Sethi, Akshay, syth, Peter, Poupart, Pascal
Format: Article
Language:English
Subjects:
Coders
Encoders-Decoders
Graphical representations
Graphs
Knowledge representation
Machine learning
Recommender systems
Social networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422