This is my solution to three assignments of CS224w.
CS224W: Machine Learning with Graphs (Stanford / Fall 2019) is
an interesting class, which teaches you how to perform machine learning algorithms with graphs.
As we all konw, networks are a fundamental tool for modeling complex social, technological, and biological systems. And we can learn the folloing content in this course:
- How to represent networks using large-scale datasets?
- How to analyse massive networks which provide several computational, algorithmic, and modeling challenges?
- How to use machine learning techniques and data mining tools apt to study their underlying network structure and interconnections?
Note: If you consult my source codes that you may want to incorporate into your algorithm or system, you should clearly cite references in your codes.
- Assignment 0
- Analyzing the Wikipedia voters network
- Further Analyzing the Wikipedia voters network
- Finding Experts on the Java Programming Language on StackOverflow
- Assignment 1
- Network Characteristics
- Structural Roles: Rolx and ReFex
- Community detection using the Louvain algorithm
- Spectral clustering
- Assignment 2
- Node Classification
- Node Embeddings with TransE
- GNN Expressiveness
- GNN training
- Assignment 3
- Bowtie Structure of Non-Web Networks
- Link Analysis
- Decision-based Cascades: A Local Election
- Influence Maximization
- snap.py
- networkX
- pandas
- numpy
- matplotlib