Ekaterina Sirazitdinova

Graph Neural Networks: What’s behind the Hype?

How does AI predict traffic, recommend friends, and discover new drugs? Learn how Graph Neural Networks derive insights from complex, unstructured data.

Graph Neural Networks: What’s behind the Hype?
#1about 2 minutes

Why graph neural networks excel with unstructured data

Graph neural networks are uniquely suited for unstructured data like 3D meshes and social networks where traditional CNNs struggle.

#2about 3 minutes

Reviewing core concepts from graph theory

Key graph theory concepts are explained, including nodes, edges, directed vs undirected graphs, and homogeneous vs heterogeneous graphs.

#3about 2 minutes

Choosing the right data structure for graphs

An adjacency matrix is suitable for small graphs, while an adjacency list is more spatially efficient for large, sparse graphs.

#4about 3 minutes

A brief refresher on deep learning fundamentals

The core deep learning process of training and inference is reviewed, along with the distinction between supervised and unsupervised learning.

#5about 6 minutes

Exploring graph, node, and edge level prediction tasks

GNNs can perform predictions at the graph level (molecule properties), node level (community detection), and edge level (recommendation systems).

#6about 4 minutes

Understanding the GNN training and data splitting process

GNNs are trained using the message passing algorithm to create node embeddings, followed by a transductive split for training and validation sets.

#7about 2 minutes

Frameworks and resources for building GNNs

Popular frameworks like DGL, PyTorch Geometric, and TensorFlow GNN simplify the implementation of graph neural networks.

#8about 1 minute

Summary of key concepts in graph neural networks

The talk concludes with a recap of key takeaways, including graph modeling, data representation, prediction tasks, and the message passing algorithm.

#9about 3 minutes

Q&A on data leakage, knowledge graphs, and embeddings

The Q&A session addresses audience questions about data leakage in transductive splits, applying GNNs to semantic knowledge graphs, and comparing graph embeddings to word embeddings.

Related jobs
Jobs that call for the skills explored in this talk.

Remote

Name of

Name of

Remote
Intermediate
PHP
Java
+1

Matching moments

Using geometric deep learning for molecular data
07:17 MIN

Using geometric deep learning for molecular data

Geometric deep learning for drug discovery

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Experimenting with different machine learning model approaches
06:24 MIN

Experimenting with different machine learning model approaches

Shoot for the moon - machine learning for automated online ad detection

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Representing complex data with knowledge graphs
03:48 MIN

Representing complex data with knowledge graphs

Large Language Models ❤️ Knowledge Graphs

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Understanding the fundamentals of graph databases
04:34 MIN

Understanding the fundamentals of graph databases

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Modeling connected data with graph databases
05:35 MIN

Modeling connected data with graph databases

Cyber Sleuth: Finding Hidden Connections in Cyber Data

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Resources for learning to build with knowledge graphs
02:38 MIN

Resources for learning to build with knowledge graphs

Give Your LLMs a Left Brain

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Q&A on graph databases for cybersecurity
15:40 MIN

Q&A on graph databases for cybersecurity

Cyber Sleuth: Finding Hidden Connections in Cyber Data

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Exploring real-world use cases for knowledge graphs
02:25 MIN

Exploring real-world use cases for knowledge graphs

Knowledge graph based chatbot

Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.

Featured Partners

Related Videos

See all videos
A beginner’s guide to modern natural language processing56:46

A beginner’s guide to modern natural language processing

Jodie Burchell

DALL·E Flow: when neural search meets generative art28:55

DALL·E Flow: when neural search meets generative art

Han Xiao

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j46:51

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j

Knowledge graph based chatbot24:44

Knowledge graph based chatbot

Tomaz Bratanic

Large Language Models ❤️ Knowledge Graphs29:11

Large Language Models ❤️ Knowledge Graphs

Michael Hunger

Martin O'Hanlon - Make LLMs make sense with GraphRAG24:42

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Martin O'Hanlon

Trends, Challenges and Best Practices for AI at the Edge29:50

Trends, Challenges and Best Practices for AI at the Edge

Ekaterina Sirazitdinova

Multimodal Generative AI Demystified56:55

Multimodal Generative AI Demystified

Ekaterina Sirazitdinova

Related Articles

View all articles
AV
Admir Video
gif
gif
DC
Daniel Cranney
How to Use Generative AI to Accelerate Learning to Code
It’s undeniable that generative-AI and LLMs have transformed how developers work. Hours of hunting Stack Overflow can be avoided by asking your AI-code assistant, multi-file context can be fed to the AI from inside your IDE, and applications can be b...
How to Use Generative AI to Accelerate Learning to Code
DD
Dilek Demir
Data Science & more: The Lopez dilemma
Catwalk, Data Science, Hollywood, Google Images, Haute Couture, StackOverflow, Comfort Zone, Dota 2 and Versace – all these topics are connected and influenced by each other. Read here how and why!In 2000 Jennifer Lopez's green Versace dress went vi...
Data Science & more: The Lopez dilemma
EM
Eli McGarvie
13 NEW AI Tools That Use ChatGPT 🤯
Our dear friend Bill Gates has recently suggested that the ChatGPT revolution is as big as the invention of mobile phones and the internet. So we thought it would be interesting to put together a list of all the useful applications that are powered b...
13 NEW AI Tools That Use ChatGPT 🤯

From learning to earning

Jobs that call for the skills explored in this talk.