Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
❤️ Become The AI Epiphany Patreon ❤️
👨👩👧👦 Join our Discord community 👨👩👧👦
In this video I cover “Neural Sheaf Diffusion:
A Topological Perspective on Heterophily and Oversmoothing in GNNs“ paper. The paper takes ideas from the sheaf theory - a branch of algebraic topology - and combines them with GNNs, enriching them with a rich geometric structure (sheaves) achieving provably more expressive diffusion-based graph neural networks!
It took a lot of time to prepare this video and read everything that was necessary as a background reading - check out the resource section below for how to get started!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper:
Truly gentle introduction to sheaves:
✅ A Very Elementary Introduction to Sheaves:
✅ Opinion dynamics on discourse sheaves:
✅ Sheaf Neural Networks:
Blogs:
✅ Blog accompanying the paper:
✅ Differential geometry and algebraic topology papers overview:
✅ Beginner intro to topology:
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00:00 Gentle intro to sheaf theory and algebraic topology
00:12:00 Making it less abstract: examples from sheaf theory
00:23:50 Formal terminology
00:27:40 Sheaf Laplacian dissected
00:40:00 The separation power of sheaf diffusion
00:53:00 Dirichlet energy and converging to harmonic space
01:01:05 Neural Sheaf Diffusion GNN
01:06:00 Results and outro (feedback appreciated)
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 BECOME A PATREON OF THE AI EPIPHANY ❤️
If these videos, GitHub projects, and blogs help you,
consider helping me out by supporting me on Patreon!
The AI Epiphany -
One-time donation -
Huge thank you to these AI Epiphany patreons:
Eli Mahler
Kevin Stone
Petar Veličković
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💼 LinkedIn -
🐦 Twitter -
👨👩👧👦 Discord -
📺 YouTube -
📚 Medium -
💻 GitHub -
📢 AI Newsletter -
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#sheaftheory #algebraictopology #oversmoothing #heterophily
1 view
2
0
3 years ago 01:08:06 1
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs