# CS224W: Machine learning with graphs

## Lecture 1
### Lecture 1.1
This lecture covers the motivation of the graphs.

### Lecture 1.2 - Applications of Graph ML

### Lecture 1.3 - Choice of Graph Representation​

## Lecture 2
### Lecture 2.1 - Traditional Feature-based Methods: Node
### Lecture 2.2 - Traditional Feature-based Methods: Link
### Lecture 2.3 - Traditional Feature-based Methods: Graph

## Lecture 3
### Lecture 3.1 - Node Embeddings
### Lecture 3.2-Random Walk Approaches for Node Embeddings
### Lecture 3.3 - Embedding Entire Graphs

## Lecture 4
### Lecture 4.1 - PageRank

### Lecture 4.2 - PageRank: How to Solve?
### Lecture 4.3 - Random Walk with Restarts

### Lecture 4.4 - Matrix Factorization and Node Embeddings


## Lecture 5
### Lecture 5.1 - Message passing and Node Classification

### Lecture 5.2 - Relational and Iterative Classification

### Lecture 5.3 - Collective Classification

## Lecture 6
### Lecture 6.1 - Introduction to Graph Neural Networks

### Lecture 6.2 - Basics of Deep Learning

### Lecture 6.3 - Deep Learning for Graphs

## Lecture 7
### Lecture 7.1 - A general Perspective on GNNs

### Lecture 7.2 - A Single Layer of a GNN
### Lecture 7.3 - Stacking layers of a GNN

## Lecture 8
### Lecture 8.1 - Graph Augmentation for GNNs
### Lecture 8.2 - Training Graph Neural Networks
### Lecture 8.3 - Setting up GNN Prediction Tasks

## Lecture 9
### Lecture 9.1 - How Expressive are Graph Neural Networks
### Lecture 9.2 - Designing the Most Powerful GNNs
assuming its one hot vector

## Lecture 10
### Lecture 10.1-Heterogeneous & Knowledge Graph Embedding
### Lecture 10.2 - Knowledge Graph Completion
### Lecture 10.3 - Knowledge Graph Completion Algorithms


## Lecture 11
### Lecture 11.1 - Reasoning in Knowledge Graphs
### Lecture 11.2
### Lecture 11.3 - Query2box: Reasoning over KGs

## Lecture 12
### Lecture 12.1-Fast Neural Subgraph Matching & Counting
### Lecture 12.2 - Neural Subgraph Matching
### Lecture 12.3 - Finding Frequent Subgraphs

## Lecture 13
### Lecture 13.1 - Community Detection in Networks
### Lecture 13.2 - Network Communities
### Lecture 13.3 - Louvain Algorithm
### Lecture 13.4 - Detecting Overlapping Communities

## Lecture 14
### Lecture 14.1 - Generative Models for Graphs
### Lecture 14.2 - Erdos Renyi Random Graphs
### Lecture 14.3 - The Small World Model
### Lecture 14.4 - Kronecker Graph Model

## Lecture 15
### Lecture 15.1 - Deep Generative Models for Graphs

### Lecture 15.2 - Graph RNN: Generating Realistic Graphs

### Lecture 15.3 - Scaling Up & Evaluating Graph Gen
### Lecture 15.4 - Applications of Deep Graph Generation

## Lecture 16
### Lecture 16.1 - Limitations of Graph Neural Networks
### Lecture 16.2 - Position-Aware Graph Neural Networks

### Lecture 16.3 - Identity-Aware Graph Neural Networks

### Lecture 16.4 - Robustness of Graph Neural Networks

## Lecture 17
### Lecture 17.1 - Scaling up Graph Neural Networks

### Lecture 17.2 - GraphSAGE Neighbor Sampling

### Lecture 17.3 - Cluster GCN: Scaling up GNNs

### Lecture 17.4 - Scaling up by Simplifying GNNs