ML with Graphs

This page includes CS224W Stanford note page.

My notes and all documents could be found in Baidu Cloud with code 2rlj . And also in Google Drive .

And link of snap documentation

HWs

Next

Same Prof.

• CS246: Mining Massive Datasets (Winter 2020) : Data Mining & Machine Learning for Big Data.

• CS341: Project in Data Mining (Spring 2020)

Other Courses:

• CS229: Machine Learning

• CS230: Deep Learning

• MSE231: Computational Social Science

• MSE334: The Structure of Social Data

• CS276: Information Retrieval and Web Search

• CS245: Database System Principles

• CS347: Transaction Processing & Databases

Contents:

• 1. Introduction: Structure of Graphs
  • 1.1 Introduction
  • 1.2 Graph
  • 1.3 Book Read
  • 1.4 HW0
• 2. Properties of Networks and Random Graph Models
  • 2.1 Properties
  • 2.2 Erolos-Renyi Random Graph Model
    • 2.2.1 Paper Read
  • 2.3 The Small-world Model
    • 2.3.1 Book Read
  • 2.4 Kronecker Graph Model
  • 2.5 HW1 - q1
• 3. Motifs and Structral Rules in Network
  • 3.1 Subgraphs
  • 3.2 Role
  • 3.3 HW1 - q2
• 4. Community Structure in Networks
  • 4.1 Edge overlap
  • 4.2 Network Communities
  • 4.3 Overlapping Communities
  • 4.4 HW1 - q3
• 5. Spectral Clustering
  • 5.1 Concepts
  • 5.2 Spectral Clustering
  • 5.3 K Clustering
  • 5.4 Motif-based spectral clustering
  • 5.5 HW1 - q4
• 6. Message Passing and Node Classification
  • 6.1 Correlations
  • 6.2 Collectivce classification
  • 6.3 Probabilistic Relational Classifier
  • 6.4 Iterative Classification
  • 6.5 Brief Propagation
• 7. Graph Representation Learning
  • 7.1 Introcution
  • 7.2 Node Embedding
  • 7.3 Random Walk
  • 7.4 Node2Vec
  • 7.5 TransE
  • 7.6 Graph Embedding
  • 7.7 HW2 Q123
• 8. Graph Neural Networks
  • 8.1 Introduction
  • 8.2 GCN
  • 8.3 Graph SAGE
  • 8.4 Graph Attention Networks
  • 8.5 Test Results
• 9. Hands-on
• 10. Graph RNN
  • 10.1 GCN review
  • 10.2 Graph Generation
  • 10.3 Graph RNN
  • 10.4 Tractability
  • 10.5 Applications
• 11. PageRank
  • 11.1 Web
  • 11.2 PageRank
  • 11.3 Examples
  • 11.4 HW3 Q1
  • 11.4 HW3 Q2
• 12. Network Effects And Cascading Behaviour
  • 12.1 Decision Based Diffusion
  • 12.2(13) Probabilistic Diffusion
    • 12.2.1 Basic Reproductive Number
    • 12.2.2 Epidemic Model
    • 12.2.2 Application Rumor spread
  • 12.3 Independent Cascade Model
• 14. Influence Maximization
  • 14.1 Linear Threshold Model
  • 14.2 Independent Cascade Model
  • 14.3 Influential Maximization (of ICM)
• 15. Outbreak Detection
  • 15.1 Introduction
  • 15.2 CELF
• 16. Network Evolution
  • 16.1 Denfication and Diameter
  • 16.2 Temporal Networks
• 17. Reasoning over Knowledge Graphs
  • 17.1 Link prediction
  • 17.2 Path Queries
  • 17.3 Conjunctive Queries
  • 17.4 Query2Box
• 18. Limitations of GNN
  • 18.1 Limitation : Graph Structure
  • 18.2 Limitation : Graph Noise
  • 18.2 Future Directions
• 19. Applications of GNN
  • 19.1 GNN recommendation (PinSage)
  • 19.2 Heterogeneous GNN (Decagon)
  • 19.3 Goal-directed generation (GCPN)