Graph Machine Learning and Random Graph Models

Explore the theoretical foundations of graph neural networks (GNNs) through the lens of random graph models in this 54-minute conference talk. Delve into the random geometric graph model from probability and statistics to understand how graph machine learning algorithms behave on large-scale random graphs. Examine the convergence properties and stability characteristics of deep graph architectures, gaining insights into the mathematical principles that govern GNN performance. Learn how theoretical computer science intersects with graph learning through rigorous analysis of random graph structures and their implications for machine learning applications.