Deep learning with dynamic graph neural networks

Показать описание

Graph machine learning has become very popular in recent years in the machine learning and engineering communities. In this video, we explore the math behind some of the most popular graph neural network algorithms!

Support the channel by liking, commenting, subscribing, and recommend this video to your friends, coworkers, or colleagues if you think they'll find this video valuable!

Other Videos in this Series

My Links:

Other Links:

Jacob Heglund

Рекомендации по теме

Комментарии

I would love to see a new update video on the topic in 2023. I am using GNNs for my PhD

augustoandre

The cool guy appeared from nowhere, dropped top-quality content, and just disappeared.

contentconsumer

Really well-presented video and a nice explanation about TGN. Thanks for that!

otaviocx

Hi, Jacob! How are you? I'm an undergraduate student from Brazil and I'm working exactly on the problem TGN tries to address (Representation Learning for Event Graphs). Unfortunately, I didn't have the chance to really dig deeper into the paper, but it looks a lot like a mix between a standard Message Passing Neural Network and some adaptations to adapt it to Dynamic Graphs, which seems very powerful from the Representation Learning point of view. Still, in the video, you talk about the fact this work uses timestamped graph events, which may be limiting. Could you elaborate on this thought? Thanks for the amazing work!

Hi Jacob, can you model COVID-19 by GCNs and implement for it. Thanks for the amazing work

ayoubfadil

Hi Jacob, check the first part of the video: it starts very pixelated/grainy. Otherwise excellent content as usual.

_________

Everything changed once you ceased sending in videos:( Lord, return; your people are waiting for you!

doyleBellamy

Hello Jacob, is there a model to use TGNN in keras or tensorflow?

YasminMohamed-icut

Hi Jacob. I'm trying to solve a problem for my internship where I somehow have to translate the edges as not being instanteneous... For example nodes are warehouses and edges are available roads in between, but I need to have something more than "instant" time. i was thinking of something like a feature on the edges which would translate to real time of a ETA of that trip, or something like that . I can't seem to find any papers that deal with that, or with node regression on dynamic graphs of any sorts..

naevan

Deep learning with dynamic graph neural networks

Deep learning with dynamic graph neural networks

TGN: Temporal Graph Networks for Deep Learning on Dynamic Graphs [Paper Explained by the Author]

Machine Learning on Dynamic Graphs and Temporal Graph Networks | MLSys 2021

Dynamic Graph CNN (DGCNN) | Lecture 43 (Part 3) | Applied Deep Learning

Friendly Introduction to Temporal Graph Neural Networks (and some Traffic Forecasting)

Dynamic Graph Neural Networks Part-1

TGN: Temporal Graph Networks for Dynamic Graphs

CSC2547 Dynamic Graph CNN for Learning on Point Cloud

AI Agents for Automation

Temporal Graph Networks (TGN) | GNN Paper Explained

HOT - Higher-Order Dynamic Graph Representation Learning with Efficient Transformers

Paper Summary: Dynamic Graph CNN for Learning on Point Cloud

The basics of spatio-temporal graph neural networks

Dynamic Graph Message Passing Networks

MAGE 1.2 - Now with Graph Machine Learning and a Full package of Dynamic Graph Algorithms

Graph Neural Networks are Dynamic Programmers

Graph Neural Networks on Point Clouds

Graph Convolutional Networks (GCNs) made simple

Dynamic Graph Neural Networks for Sequential Recommendation

Static Vs Dynamic Graph Neural Networks

3D Mesh segmentation using deep learning (Dynamic Graph CNN, DGCNN)

Dynamic Graph Neural Networks Part-2

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs | Spotlight 1-1A

KDD 2023 - WinGNN: Dynamic Graph Neural Networks with Random Gradient Aggregation Window