Hyperbolic Graph Convolutional Networks | Geometric ML Paper Explained
❤️ Become The AI Epiphany Patreon ❤️
https://www.patreon.com/theaiepiphany
👨👩👧👦 Join our Discord community 👨👩👧👦
https://discord.gg/peBrCpheKE
In this video we dig deep into the hyperbolic graph convolutional networks paper introducing a class of GCNs operating in the hyperbolic space.
Hyperbolic GCNs give exceptional results for the class of scale-free/hierarchical/tree-like graphs. I dive deep into differential geometry theory and explain how the method works.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: https://arxiv.org/abs/1910.12933
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro - why the hyperbolic space?
04:00 Graph Convolutional Networks recap
08:50 Hyperbolic space and curvature theory
15:25 Geodesics, exp, and log maps
23:00 Mapping from Euclidean to hyperbolic space
26:35 Feature transform in hyperbolic space
32:47 Aggregregation on the hyperboloid manifold
35:25 Non-linear activation with different curvatures
36:30 Holistic overview of the method
38:20 Results, Ablations, and curvature analysis
41:00 Why does curvature help?
42:05 Outro
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 - https://www.patreon.com/theaiepiphany
One-time donation - https://www.paypal.com/paypalme/theaiepiphany
Huge thank you to these AI Epiphany patreons:
Eli Mahler
Kevin Stone
Petar Veličković
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💼 LinkedIn - https://www.linkedin.com/in/aleksagordic/
🐦 Twitter - https://twitter.com/gordic_aleksa
👨👩👧👦 Discord - https://discord.gg/peBrCpheKE
📺 YouTube - https://www.youtube.com/c/TheAIEpiphany/
📚 Medium - https://gordicaleksa.medium.com/
💻 GitHub - https://github.com/gordicaleksa
📢 AI Newsletter - https://aiepiphany.substack.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#graphs #graphconvolutionalnetwork #hyperbolicspace
Видео Hyperbolic Graph Convolutional Networks | Geometric ML Paper Explained канала Aleksa Gordić - The AI Epiphany
https://www.patreon.com/theaiepiphany
👨👩👧👦 Join our Discord community 👨👩👧👦
https://discord.gg/peBrCpheKE
In this video we dig deep into the hyperbolic graph convolutional networks paper introducing a class of GCNs operating in the hyperbolic space.
Hyperbolic GCNs give exceptional results for the class of scale-free/hierarchical/tree-like graphs. I dive deep into differential geometry theory and explain how the method works.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: https://arxiv.org/abs/1910.12933
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro - why the hyperbolic space?
04:00 Graph Convolutional Networks recap
08:50 Hyperbolic space and curvature theory
15:25 Geodesics, exp, and log maps
23:00 Mapping from Euclidean to hyperbolic space
26:35 Feature transform in hyperbolic space
32:47 Aggregregation on the hyperboloid manifold
35:25 Non-linear activation with different curvatures
36:30 Holistic overview of the method
38:20 Results, Ablations, and curvature analysis
41:00 Why does curvature help?
42:05 Outro
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 - https://www.patreon.com/theaiepiphany
One-time donation - https://www.paypal.com/paypalme/theaiepiphany
Huge thank you to these AI Epiphany patreons:
Eli Mahler
Kevin Stone
Petar Veličković
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💼 LinkedIn - https://www.linkedin.com/in/aleksagordic/
🐦 Twitter - https://twitter.com/gordic_aleksa
👨👩👧👦 Discord - https://discord.gg/peBrCpheKE
📺 YouTube - https://www.youtube.com/c/TheAIEpiphany/
📚 Medium - https://gordicaleksa.medium.com/
💻 GitHub - https://github.com/gordicaleksa
📢 AI Newsletter - https://aiepiphany.substack.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#graphs #graphconvolutionalnetwork #hyperbolicspace
Видео Hyperbolic Graph Convolutional Networks | Geometric ML Paper Explained канала Aleksa Gordić - The AI Epiphany
Комментарии отсутствуют
Информация о видео
6 мая 2022 г. 13:33:40
00:42:51
Другие видео канала
10k subscribers | joining Google DeepMind, updates, AMA
Day 7: Meta NLLB - data sharding, binarization, etc. (Pt. 3)
Day 25: Open NLLB - filtering HBS (Pt 2)
Fastformer: Additive Attention Can Be All You Need | Paper Explained
Day 24: Open NLLB - back from China, analyzing spikes, preparing HBS run (Pt 2)
Day 6: Meta NLLB - data filtering (Pt. 4)
Day 24: Open NLLB - back from China, filtering HBS data (Pt 3)
Day 14: Open NLLB - Eval of our first run (English, Turkish, Hindi) (Pt 2.)
Day 4: Training 600M NLLB - data preps (Pt. 2)
Day 6: Meta NLLB - data filtering (Pt. 3)
DeepMind's Android RL Environment - AndroidEnv
Day 20: Open NLLB - analyzing HBS data (Bosnian, Croatian) (Pt 2)
Day 7: Meta NLLB - data structure & filtering (Pt. 1)
Day 11: Open NLLB - FSDP, on-boarding as a new-joiner (Pt 3.)
Day 17: Open NLLB - eval on 2 GPUs all-gather, fairseq data loading debugging session (Pt 1)
Hamel Husain - Building LLM Apps in Production
Day 28: Open NLLB - debugging fuzzy dedup, training fasttext LID (Pt 3)
Day 10: Open NLLB - evaluation data, filtering (Pt 3.)
Day 7: Meta NLLB - analyzing the training script, Jais paper (Pt. 4)
EleutherAI Pythia w/ Hailey Schoelkopf
Day 18: Open NLLB - data loading document, GitHub tasks (Pt 1 cont.)
