Graph Learning

Message passing, graph convolutions, expressivity, scaling, and the limits of graph neural networks.

  1. Why deeper graph networks face under-reaching, over-smoothing, and over-squashing—and how topology determines which remedy helps.
    Tutorial · Published Aug 08, 2026 · Updated Aug 09, 2026 · 34 min read
  2. Two derivations of graph convolution—from Laplacian spectral filters and permutation-equivariant linear maps—and what each reveals and hides.
    Tutorial · Published Aug 08, 2026 · Updated Aug 09, 2026 · 34 min read
  3. Graph neural network expressivity through multiset aggregation, the Weisfeiler--Leman test, its blind spots, and the cost of stronger models.
    Tutorial · Published Aug 08, 2026 · Updated Aug 09, 2026 · 35 min read
  4. Why permutation symmetry leads to message passing, how familiar GNNs instantiate it, and why graph Transformers still need structure.
    Tutorial · Published Aug 08, 2026 · Updated Aug 09, 2026 · 39 min read