https://github.com/kkhuang81/UniFilter
A polynomial filter using a universal basis
https://github.com/kkhuang81/UniFilter
Last synced: 3 months ago
JSON representation
A polynomial filter using a universal basis
- Host: GitHub
- URL: https://github.com/kkhuang81/UniFilter
- Owner: kkhuang81
- License: mit
- Created: 2024-05-17T14:04:05.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-06-06T07:01:43.000Z (11 months ago)
- Last Synced: 2024-06-07T08:09:02.493Z (11 months ago)
- Language: Python
- Size: 51.8 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
**UniFilter** is a polynomial graph filter utilizing a novel universal polynomial basis called **UniBasis**. This repository contains the source codes for **UniFilter**. For further details, please refer to our paper in **ICML 2024** (https://arxiv.org/abs/2405.12474). Should you encounter any issues, please reach out to Keke Huang, thanks!
## Environment Settings
- pytorch 1.7.0
- torch-geometric 1.6.1
- scipy 1.9.3
- seaborn 0.12.0
- scikit-learn 1.1.3
- ogb 1.3.1
- gdown
## Datasets
Please acquire all the data from ChebNet II and put the data in the subfolder './data'.
The ogb datasets (ogbn-arxiv and ogbn-papers100M) and non-homophilous datasets (from [LINKX](https://arxiv.org/abs/2110.14446) ) can be downloaded automatically.
## Folders
Please create a folder named 'pretrained' before running.
## Citation
Please cite our paper if it is relevant to your work, thanks!