hedongxiao-tju / hog-gcn

HOG-GCN

Source code for AAAI2022 "[Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily"

Environment Settings

• python == 3.7
• Pytorch == 1.1.0
• Numpy == 1.16.2

Usage

python main_homo.py -dataset cora

• dataset: including [Texas, Cornell, Wisconsin, Film, Cora, Citeseer, Pubmed]

Reference

If you make advantage of HOG-GCN in your research, please cite the following in your manuscript:

Wang, Tao, et al. "Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily." In AAAI. 2022.

License

Tianjin University

hog-gcn's Issues

Poor performance on some classic heterophilic benchmarks

Hi,

I apply the code implementation on more classic heterophilic graphs such as Chameleon, Actor, and Squirrel, which are widely used in prior related works (H2GCN, GGCN, CPGNN, GeomGCN, etc.). However, I can not get the desired results, sometimes even less effective than vanilla GCN and GraphSAGE. Would you mind providing the best hyperparameters of HOG-GCN on these datasets?

In my opinion, I think the strong performance on hetero graphs exhibited in the paper mainly comes from the first part of Eq.(10), i.e., Z^(l-1)W_e, and you adopt MLP to output:

HOG-GCN/models_homo.py

Line 99 in 9e3844e

output = self.MLP(emb)

. Because when I adopt it on GraphSAGE, it can also achieve the best results, even better than HOG-GCN.