Graph Learning
Message passing, graph convolutions, expressivity, scaling, and the limits of graph neural networks.
- Why deeper graph networks face under-reaching, over-smoothing, and over-squashing—and how topology determines which remedy helps.
- Two derivations of graph convolution—from Laplacian spectral filters and permutation-equivariant linear maps—and what each reveals and hides.
- Graph neural network expressivity through multiset aggregation, the Weisfeiler--Leman test, its blind spots, and the cost of stronger models.
- Why permutation symmetry leads to message passing, how familiar GNNs instantiate it, and why graph Transformers still need structure.