GithubHelp home page GithubHelp logo

dsl-lab / specformer Goto Github PK

View Code? Open in Web Editor NEW
64.0 5.0 12.0 29.59 MB

Transformer-based Spectral Graph Neural Networks

License: GNU General Public License v3.0

Python 100.00%
geometric-deep-learning graph-neural-networks spectral-gnns

specformer's Introduction

Specformer

Code of Specformer: Spectral Graph Neural Networks Meet Transformers

How to run

  • For node-level task, e.g., signal regression and node classification, you should first run preprocess_node_data.py to generate .pt files for each dataset.
  • For graph-level taks, you can direcly run dgl_main.py.

Q&A

Any suggestion/question is welcome.

Reference

If you make advantage of Specformer in your research, please cite the following in your manuscript:

@inproceedings{specformer2023,
  author={Deyu Bo and 
          Chuan Shi and
          Lele Wang and
          Renjie Liao},
  title={Specformer: Spectral Graph Neural Networks Meet Transformers},
  booktitle = {{ICLR}},
  publisher = {OpenReview.net},
  year      = {2023}
}

specformer's People

Contributors

bdy9527 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

specformer's Issues

pygdataclass is required, but it is missing in repo

In get_dataset.py

from dataclasses import *
from dgldataclass import DglGraphPropPredDataset, DglPCQM4Mv2Dataset, DglZincDataset
from pygdataclass import PygGraphPropPredDataset

dgldataclass.py exists, but pygdataclass.py does not. It might be issue??

There is a significant gap compared to the reported ACC of GCN on CiteSeer

I found that some data processing was done during testing on Citeseer, so I tested the performance of GCN on the processed data and obtained an ACC of 84.86 ± 0.14, which is significantly different from the results reported in the article. GCN is set to two layers, with an hidden dim is 512.

Problems in the get_dataset file

from dataclass import *
from pygdataclass import PygGraphPropPredDataset

The custom "pygdataclass" and "pygdataclass" modules are not a standard Python package or library. But I can't find the files for these two modules in the project.

Looking forward to your reply thanks!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.