Graph Convolutional Network

Fact

A neural network that learns from graph links and builds node representations.

In Plain Words

A Graph Convolutional Network is like judging a house by its neighborhood. The shops, the streets, the foot traffic tell you more than the floor plan alone.

It learns from connections, not just single items. You meet it in social apps, recommendations, and molecule research.

Related Concepts

• Neural Network
• Convolutional Neural Network
• Vector Embedding
• Knowledge Representation

Neural-network
A Graph Convolutional Network is a neural network built for graph data.

CNN
It borrows the convolution idea, but its neighbors are graph links, not grid squares.

Embedding
It turns nodes or whole graphs into vectors computers can use.

KR
It helps model things and the links between them.