Graph Neural Networks: Learning from Connections, Not Just Data

Update: 2025-09-30

Description

This episode breaks down what graph neural networks (GNNs) are and why they matter. You’ll learn how GNNs use nodes and edges to represent relationships and how message passing lets models make sense of social, biological, and networked data. We’ll also cover recent advancements like PGNN for multi-modal graphs and common pitfalls like scalability and over-smoothing.

Comments

In Channel

Graph Neural Networks: Learning from Connections, Not Just Data

2025-09-3031:15

Neuro-Symbolic AI: Combining Learning With Logic

2025-09-1624:49

LLMs in Chip Design: How AI Is Entering the Hardware Workflow

2025-09-0220:08

How Embeddings and Vector Databases Power Generative AI

2025-08-1918:32

Agentic AI: What Happens When Models Start Acting

2025-08-0519:11

Understanding Attention: Why Transformers Actually Work

2025-07-2220:27

Markov Chains, Monte Carlo, and HMC: A Deep Dive

2025-07-0823:54

The Model Context Protocol (MCP): Making LLMs Actually Useful

2025-06-2416:52

Generative Adversarial Networks (GANs) Explained: From DL Basics to Real-World Training Tips

2025-06-1027:39

Bayesian vs. Frequentist Thinking in Marketing Mix Modeling

2025-05-2722:46

00:00

Graph Neural Networks: Learning from Connections, Not Just Data

#box-pro-ellipsis-176153740836315{-webkit-line-clamp:2;}Graph Neural Networks: Learning from Connections, Not Just Data

Graph Neural Networks: Learning from Connections, Not Just Data

Mo Bhuiyan via NotebookLM

Graph Neural Networks: Learning from Connections, Not Just Data