Graph Neural Networks from Theory to Applications

Speaker:  Irwin King – Hong Kong, Hong Kong
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

Graph Neural Network (GNN) is a type of neural network designed to process graph-structured data. This includes data from social networks, citation networks, traffic networks, semantic networks, polygon meshes, and molecular structures. Besides handling non-Euclidean data, GNNs can also process Euclidean data like sentences, images, and videos. One primary technique used in GNN is graph embedding, which involves projecting the elements in a graph—such as nodes, edges, substructures, or the entire graph—into a low-dimensional space. This is done while preserving the structural information of the graph. In this presentation, we will discuss recent developments in GNNs. These developments include advancements in graph embedding, convolution-based methods, and attention networks. We will also explore their intriguing applications in social computing, such as node classification, link prediction, and social recommendations.

About this Lecture

Number of Slides:  60
Duration:  5 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.