Skip to content

Utilities for generating real-world-like graphs with customizable node features using the LFR algorithm.

Notifications You must be signed in to change notification settings

Gandagorn/LFRGraphGenerator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project LFR Graph Generation and Evaluation

Masterproject 2021

Utilities for generating real-world-like graphs with customizable attributes and features using the Lancichinetti-Fortunato-Radicchi (LFR) algorithm. The goal of this project was to generate benchmark graphs to evaluate the influence of homophily on various node classification models.

Graph Generation

Efficiently generate artificial benchmark graphs with realistic node degree and community size distribution using the LFR algorithm. Can control for

  • Number of nodes and average degree
  • Edge-Homophily-Ratio
  • Community size and node degree distributions

Graph Evaluation

Training and evaluation of several GNN and MLP models on the node classification task using graphs of different homophily. This also includes custom implementations for some GNN models. The models include

  • Graph Convolutional Network (GCN)
  • Graph Attention Network (GAT)
  • Simple Graph Convolution (SGC)
  • Graph Sample and Aggregate (GraphSAGE)
  • H2GCN
  • MLP as baseline

About

Utilities for generating real-world-like graphs with customizable node features using the LFR algorithm.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published