Skip to content

Shiy-Li/MQE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MQE

This repository is the official implementation of "Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation", accepted by CIKM 2024.

Training on Colab

Click the "Open in Colab" button to quickly reproduce the results in the Google Colab environment.

Setup

conda create -n MQE python=3.8
conda activate MQE
pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cu121
pip install --no-index torch-scatter -f https://pytorch-geometric.com/whl/torch-2.1.2+cu121.html
pip install --no-index torch-sparse -f https://pytorch-geometric.com/whl/torch-2.1.2+cu121.html
pip install --no-index torch-cluster -f https://pytorch-geometric.com/whl/torch-2.1.2+cu121.html
pip install --no-index torch-spline-conv -f https://pytorch-geometric.com/whl/torch-2.1.2+cu121.html
pip install torch-geometric

Cite

If you compare with, build on, or use aspects of this work, please cite the following:

@inproceedings{li2024noise,
author = {Li, Shiyuan and Liu, Yixin and Chen, Qingfeng and Webb, Geoffrey I. and Pan, Shirui},
title = {Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation},
year = {2024},
doi = {10.1145/3627673.3679758},
booktitle = {Proceedings of the 33rd ACM International Conference on Information and Knowledge Management},
pages = {1255–1265},
}

About

[CIKM'24] Noise-Resilient UGRL

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages