Skip to content
/ NDLS Public
forked from zwt233/NDLS

Node Dependent Local Smoothing for Scalable Graph Learning(NeurIPS'21, Spotlight)

Notifications You must be signed in to change notification settings

PKU-DAIR/NDLS

 
 

Repository files navigation

Node Dependent Local Smoothing for Scalable Graph Learning

Requirements

Environments: Xeon Gold 5120 (CPU), 384GB(RAM), TITAN RTX (GPU), Ubuntu 16.04 (OS)

The PyTorch version we use is torch 1.7.1+cu110. Please refer to the official website -- https://pytorch.org/get-started/locally/ -- for the detailed installation instructions.

To install other requirements:

pip install -r requirements.txt

Training

To train the model(s) in the paper, run this command:

cd src; python train.py --dataset cora/citeseer/pubmed

Please refer to the Appendix for the detailed hyperparameters.

Node Classification Results

  1. Transductive Setting:

    transductive

  2. Inductive Setting:

    inductive

  3. Efficiency Comparison:

    efficiency

About

Node Dependent Local Smoothing for Scalable Graph Learning(NeurIPS'21, Spotlight)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%