[Deep Graph Learning] 5.2 Node permutation equivariance in GNNs

#DGL #GCN #GNN 📚🔗 The CLEAN summary map of the DGL videos 5.1 to 5.4 can be found at: https://drive.google.com/file/d/16p0b-wRV79spwUrtg9WqLjZjfOLz3oZi/view?usp=sharing 📚🔗 The ANNOTATED summary map of the DGL videos 5.1 to 5.4 can be found at: https://drive.google.com/file/d/1nIBsKMIYWBu2XJQfCZ3pkMIBDLSJv0A_/view?usp=sharing 👉 Reading material: 1. DropGNN: Papp PA, Martinkus K, Faber L, Wattenhofer R. DropGNN: Random dropouts increase the expressiveness of graph neural networks. Advances in Neural Information Processing Systems. 2021. 2. GIN: Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? ICLR 2019. 3. WL test: Boris Weisfeiler and AA Lehman. A reduction of a graph to a canonical form and an algebra arising during this reduction. Nauchno-Technicheskaya Informatsia, 2(9):12–16, 1968. Unlock the world of Deep Graph Learning with our new video series! 🚀 Dive into the mathematical foundations of graph neural networks using an intuitive approach and the power of linear algebra. 🙏 Special thanks to Simon Prince, Alex Fornito, Andrew Zalesky, Edward Bullmore, Jure Leskovec and all those who shared their passion about graphs and deep learning. Textbooks: • Simon Prince; Understanding Deep Learning (2023); https://github.com/udlbook/ • Bullmore, Edward T., Fornito, Alex, and Zalesky, Andrew; Fundamentals of Brain Network Analysis-Academic Press, Elsevier (2016)