Thanks to visit codestin.com
Credit goes to github.com

Skip to content
/ FedDCL Public

Official PyTorch implementation for the paper FedDCL: Federated Diffusion-enhanced Contrastive Learning for Graph Anomaly Detection.

Notifications You must be signed in to change notification settings

weihus/FedDCL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FedDCL: Federated Diffusion-enhanced Contrastive Learning for Graph Anomaly Detection

The proposed framework

Requirments

This code requires the following:

  • Python>=3.8
  • PyTorch>=2.1.0
  • torch-cluster>=1.6.2
  • torch-scatter>=2.1.2
  • torch-sparse>=0.6.18
  • torch-spline-conv>=1.2.2
  • torch-geometric>=2.6.1
  • Numpy>=1.24.4
  • Scipy>=1.10.1
  • Scikit-learn>=1.3.2
  • Networkx>=2.7
  • Tqdm>=4.67.1
  • DGL==0.4.3
  • metis>=0.2a5

Running the experiments

Step 1: Train Fed-CoLA

python run.py --seed 0 --clients 5 --dataset cora

Step 2: Train FedDCL

python train.py --seed 0 --clients 5 --dataset cora

Step 3: Infer FedDCL

python infer.py --client_idx 0 --seed 0  --clients 5 --dataset cora

About

Official PyTorch implementation for the paper FedDCL: Federated Diffusion-enhanced Contrastive Learning for Graph Anomaly Detection.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages