Learning Graph Representations

TL;DR

This paper reviews recent advances in graph neural networks, focusing on methods like graph convolutional neural networks, autoencoders, and spatio-temporal models for learning effective graph representations for various applications.

Contribution

It provides an overview of different GNN architectures and discusses how they learn low-dimensional graph representations for downstream tasks.

Findings

GNNs effectively capture complex relationships in large graph datasets.

Graph autoencoders enable unsupervised learning of graph embeddings.

Spatio-temporal GNNs model dynamic graph data for real-time applications.

Abstract

Social and information networks are gaining huge popularity recently due to their various applications. Knowledge representation through graphs in the form of nodes and edges should preserve as many characteristics of the original data as possible. Some of the interesting and useful applications on these graphs are graph classification, node classification, link prediction, etc. The Graph Neural Networks have evolved over the last few years. Graph Neural Networks (GNNs) are efficient ways to get insight into large and dynamic graph datasets capturing relationships among billions of entities also known as knowledge graphs. In this paper, we discuss the graph convolutional neural networks graph autoencoders and spatio-temporal graph neural networks. The representations of the graph in lower dimensions can be learned using these methods. The representations in lower dimensions can be used further for downstream machine learning tasks.