Representation Learning for Dynamic Graphs: A Survey

By Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, Pascal Poupart, Karsten M. Borgwardt. Journal of machine learning research, 2019

638 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/8a8e4fa580a81ba2fcb86965f323709cafcab275

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Graph Representation Learning in Biomedicine and Healthcare (2021, positive): “…17,18 ; graph neural networks 19–21 (GNNs); representation learning for homogeneous and heterogeneous graphs 22–24 , solely heterogeneous graphs 25 and dynamic graphs 26 ; data fusion 27 ; network propagation 28 ; topological data analysis 29 (TDA); and the creation of biomedical networks 9,29–32 .”
Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey (2020, methodology): “Predictions can be done in a time-conditioned or time-predicting manner [11].”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Following the terminology in (32), a neural model for dynamic graphs can be regarded as an encoder-decoder pair, where an encoder is a function that maps from a dynamic graph to node embeddings, and a decoder takes as input one or more node embeddings and makes a prediction based on these, e.”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, background): “As a popular research topic, deep learning for dynamic graph data mining [182], [183] has shown its effectiveness in supporting many dynamic graph analysis tasks, such as node clustering and graph classiﬁcation [60].”