CS224w 图神经网络 01-intro

Network: Networks are a general language for describing complex systems of interacting entities.

Two types of Networks/Graphs:

Networks(also known as Natural Graphs):

Society; Communication system; Interactions between genes regulate life; thoughts

Information Graphs:

Information/knowledge are organized and linked

Scene graphs: how objects in a scene relate

Similarity networks: take data, connect similar points //相似网络

Sometimes the distinction is blurred

How are these systems organized? What are their design properties?

Behind many systems there is an intricate wiring diagram, a network, that defines the interactions between the components. We will never be able to model and predict these systems unless we understand the networks behind them.

Graphs: Machine Learning

How do we take advantage of relational structure for better prediction?

Complex domains(knowledge, text, images, etc.) have rich relational structure, which can be represented as a relational graph. By explocitly modeling relationships we achieve better performance.

Why Networks? Why Now?

Universal language for describing complex data

Shared bocabulary between fields

Data availability and computational challenges

Impact!

Ways to Analyze Networks

Predict the type/color of a given node: Node classification

Predict whether two nodes are linked: Link prediction

Identify densely linked clusters of nodes: Community detection

Measure similarity of two nodes/networks: Network similarly

Structure of Graphs

A network is a collection of objects where some pairs of objects are connected by links

Components of a Network

Objects: nodes, vertices $N$

Interactions:links,edges $E$

System:network,graph G (