Skip to content

hmtbgc/HFLR-ICASSP2025

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

HFLR: Optimizing GNN Training via High-Fixed-Low-Resampling

Accepted by ICASSP 2025

How to Run

Download dataset from Google Drive link or BaiduYun link(code:f1ao) and put it at correct place:

/home/user/tot_code
│   
└───GraphSAGE
|   
└───GraphSAINT
| 
└───dataset/
|   |   flickr/
|   |   ogbn-arxiv/
|   |   ...

Only four files are needed: adj_full.npz, class_map.json, feats.npy and role.json. These public datasets are collected by GraphSAINT and are irrelevant to this paper.

For graph AMiner, you can download it from Google Drive link or BaiduYun link(code:l0pe).

If you want to run certain algorithm(e.g. HFLR):

cd HFLR
bash run.sh

Results will be saved at log directory.

About

HFLR: Optimizing GNN Training via High-Fixed-Low-Resampling

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors