Загрузка страницы

Graph Attention Networks (GAT) | GNN Paper Explained

In this video, I do a deep dive into the graph attention network paper!

GATs have a lot in common with transformers a reason more to keep an eye out for them!

You'll learn about:
✔️ Basic graph theory
✔️ All the nitty-gritty details behind GAT

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ GAT website: https://petar-v.com/GAT/
✅ GAT paper: https://arxiv.org/abs/1710.10903
✅ M. Bronstein's blog: https://towardsdatascience.com/do-we-need-deep-graph-neural-networks-be62d3ec5c59
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⌚️ Timetable:
00:00 - A note on geometric deep learning
00:50 - Graph theory basics
08:35 - Intro to GATs (related work)
10:15 - A detailed explanation of the method
16:20 - A multi-head version of the GAT
19:05 - Visualizations, spatial pooling, GNN depth
21:20 - A recap of GAT properties
23:35 - Receptive field of spatial GNNs
24:35 - Datasets, transductive vs inductive learning
30:35 - Results on transductive/inductive benchmarks
35:30 - Representations visualization (t-SNE)

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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

Much love! ❤️
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

💡 The AI Epiphany is a channel dedicated to simplifying the field of AI using creative visualizations and in general, a stronger focus on geometrical and visual intuition, rather than the algebraic and numerical "intuition".

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
👋 CONNECT WITH ME ON SOCIAL
(I'm mostly active on LinkedIn and Twitter)
LinkedIn ► https://www.linkedin.com/in/aleksagordic/
Twitter ► https://twitter.com/gordic_aleksa
Medium ► https://gordicaleksa.medium.com/

Instagram ► https://www.instagram.com/aiepiphany/
Facebook ► https://www.facebook.com/aiepiphany/

FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► https://github.com/gordicaleksa

Connect with Petar Veličković:
LinkedIn ► https://www.linkedin.com/in/petarvelickovic/
Twitter ► https://twitter.com/PetarV_93
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

#graphs #attention #deeplearning

Видео Graph Attention Networks (GAT) | GNN Paper Explained канала The AI Epiphany
Показать
Комментарии отсутствуют
Введите заголовок:

Введите адрес ссылки:

Введите адрес видео с YouTube:

Зарегистрируйтесь или войдите с
Информация о видео
21 декабря 2020 г. 19:35:42
00:37:44
Яндекс.Метрика