Bresson's Graph ML Course Lecture 8: Graph Convolutional Networks
xbresson · x · 2026-09-30
Xavier Bresson shares Lecture 8 of his Graph Machine Learning course, covering Graph Convolutional Networks in depth: convolution on grids vs graphs, shared template matching, spectral convolution, Fourier transforms, Chebyshev polynomials, an/isotropic aggregation, and architectures including ChebNet, GCN, GAT, and GatedGCN.
More from Research
- A 'wisdom gradient' for AI alignment: eliciting diverse human values bottom-up — edelwax · 2026-09-30
- Hugging Face Teams Up with os4science to Fund the Open Source Science Stack — lvwerra · 2026-09-30
- Berkeley open-sources a full humanoid robot for under $5,000 — _Stocko_ · 2026-09-30
- Meta, Stanford and Harvard open up ProgramBench leaderboard with community submissions — jyangballin · 2026-09-30
- AI's "OH MY GOD!" exclamations may actually help its reasoning — danintheory · 2026-09-30
- Poison sample selection swings LLM backdoor attack success from 3% to 80% — chhaviyadav_ · 2026-09-30