Graph Learning Meets Theoretical Computer Science

Graph learning is a branch of machine learning focusing on developing and studying methods to make predictions for vertices, subgraphs, or entire graphs. The field of graph learning has already revealed many interesting connections across various areas in theoretical computer science (TCS) and mathematics, including logic, descriptive complexity, learning theory, combinatorial optimization, and geometry. 

In this workshop, we bring together researchers in graph learning who can benefit from a TCS perspective and researchers in TCS who can engage with graph learning. Our objectives are to:

• Provide a more unified perspective on graph learning within TCS.
• Identify the major challenges arising from the current interactions between graph learning and TCS.
• Discover areas within TCS that could benefit from richer interaction with graph learning.