Stanford CS224W: ML with Graphs | 2021 | Lecture 15.1 – Deep Generative Models for Graphs

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3Ex8TsH

Jure Leskovec
Computer Science, PhD

In this lecture, we focus on deep generative models for graphs. We outline 2 types of tasks within the problem of graph generation: (1) realistic graph generation, where the goal is to generate graphs that are similar to a given set of graphs; (2) goal-directed graph generation, where we want to generate graphs that optimize given objectives/constraints. First, we recap the basics for generative models and deep generative models; then, in lectures 15.2 and 15.3 we introduce and focus on GraphRNN, https://arxiv.org/abs/1802.08773 one of the first deep generative models for graph; and finally, in lecture 15.4 we discuss GCPN, https://arxiv.org/abs/1806.02473 a deep graph generative model designed specifically for application to molecule generation.

To follow along with the course schedule and syllabus, visit:
http://web.stanford.edu/class/cs224w/

#machinelearning #machinelearningcourse