Implementing GNN Neighbor Sampler in JAX: A Practical Guide

  Рет қаралды 159

Mashaan Alshammari

Mashaan Alshammari

Күн бұрын

Пікірлер: 1
@mashaan14
@mashaan14 6 ай бұрын
Mistakes in the video (the ones that I know about 😅): - I changed the implementation for the neighbor_sampler function. It previously takes one minute to sample from Cora dataset. Now, it samples in around 10 seconds. That’s because I removed the unique function and used sparse matrices indexing. The link in the description has the new code. - In 32:54 I said that the probability of picking an edge is 1. That's actually not true, it's 1/|E|, where |E| is the number of edges in the graph. I fixed it on my github notes.
Building a Cluster-GCN Model with JAX: A Step-by-Step Guide
53:47
Mashaan Alshammari
Рет қаралды 149
Graph Attention Networks with JAX
18:39
Mashaan Alshammari
Рет қаралды 221
Enceinte et en Bazard: Les Chroniques du Nettoyage ! 🚽✨
00:21
Two More French
Рет қаралды 42 МЛН
JAX Crash Course - Accelerating Machine Learning code!
26:39
AssemblyAI
Рет қаралды 11 М.
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
Transformers (how LLMs work) explained visually | DL5
27:14
3Blue1Brown
Рет қаралды 4,2 МЛН
I made maps that show time instead of space
10:44
Václav Volhejn
Рет қаралды 606 М.
Self-/Unsupervised GNN Training
12:09
DeepFindr
Рет қаралды 19 М.
GradIEEEnt half decent: The hidden power of imprecise lines
55:02
suckerpinch
Рет қаралды 312 М.
Why has Black & White Been Abandoned? - Noclip Greatest Hits
28:44
Noclip - Video Game Documentaries
Рет қаралды 731 М.
Evolution of software architecture with the co-creator of UML (Grady Booch)
1:30:43
The Pragmatic Engineer
Рет қаралды 82 М.