GraphEDM: A Unified Framework for Machine Learning on Graphs

Register to watch this content

By submitting you agree to the Terms & Privacy Policy
Watch this content now

About this talk

There has been a surge of recent interest in learning representations for graph-structured data.

Graph representation learning methods have generally fallen into three main categories, based on the availability of labeled data.

The first, network embedding (such as shallow graph embedding or graph auto-encoders), focuses on learning unsupervised representations of relational structure.

The second, graph regularized neural networks, leverages graphs to augment neural network losses with a regularization objective for semi-supervised learning.

The third, graph neural networks, aims to learn differentiable functions over discrete topologies with arbitrary structure.

In this talk, we present our recent GraphEDM unified framework which bridges the gap between these disparate bodies.

We use GraphEDM to describe many popular graph representation learning methods such as DeepWalk and Graph Convolutional Neural Networks.

👉 Book Your Ticket Now

Categories covered by this talk

Ines Chami

Ines is a Ph.D. candidate in ICME at Stanford University, advised by Professor Christopher RĂ©. Prior to attending Stanford, she studied Mathematics and Computer Science at Ecole Centrale Paris. Her research is focused on learning representation for structured data such as graphs, with a focus on non-Euclidean embedding methods.

Proudly supported by

Want to sponsor this event? Contact Us.

Loading content...

Loading content...