Survey Lecture: Martin Grohe: The Logic of Graph Neural Networks
Thursday, May 20, 2021, 4:30pm
Speaker: Martin Grohe
Abstract:
Graph neural networks (GNNs) are a deep learning
architecture for graph structured data that has developed into a
method of choice for many graph learning problems in recent years. It
is therefore important that we understand their power. One aspect of
this is the expressiveness: which functions on graphs can be expressed
by a GNN model? Surprisingly, this question has a precise answer in
terms of logic and a combinatorial algorithm known as the Weisfeiler
Leman algorithm.
In my lecture, I will introduce the basic GNN architecture and also
some extensions, and I will explain the logical characterisations
of their expressiveness.
The talks of the UnRAVeL survey lecture 2021 will be given via Zoom every Thursday from 16:30 to 18:00:
Meeting ID: 960 4371 5437
Passcode: 039217