As companion material to the release of our (proto-)book on Geometric Deep Learning, we have curated a series of blog posts. These blogs present a “digest” version of the key ideas covered by our work, as well as insight into how these ideas developed historically. We thank Towards Data Science for kindly hosting these blogs. Thoughts, comments and any kind of feedback are all very welcome!

• Geometric Foundations of Deep Learning (Proto-book launch post)
• Towards Geometric Deep Learning I: On the Shoulders of Giants
• Towards Geometric Deep Learning II: The Perceptron Affair
• Towards Geometric Deep Learning III: First Geometric Architectures
• Towards Geometric Deep Learning IV: Chemical Precursors of GNNs
• Deriving convolution from first principles
• Expressive power of graph neural networks and the Weisfeiler-Lehman test
• Using Subgraphs for More Expressive GNNs
• Graph Neural Networks through the lens of Differential Geometry and Algebraic Topology
• Neural Sheaf Diffusion for deep learning on graphs