PairNorm
Official pytorch source code for PairNorm paper (ICLR 2020)
This code requires pytorch_geometric>=1.3.2
usage
For SGC, we use original PairNorm. Notice norm_scale is data-dependent. One can choose it from {0.1, 1, 10, 50}.
python main.py --data cora --model SGC --nlayer 40 --missing_rate 100 --norm_mode PN --norm_scale 10
For GCN or GAT, we use PairNorm-SI or SCS.
python main.py --data cora --model DeepGCN --nlayer 10 --missing_rate 100 --norm_mode PN-SI --residual 0
python main.py --data cora --model DeepGAT --nlayer 10 --missing_rate 100 --norm_mode PN-SCS --residual 0
update: normalization and PN
we have found that PN works bad with symmetric normalized adjacency matrix, originally the experiments align with the paper used row-normalized adjacency matrix. What's more, we also found a small bug in the old experiments with using PN for GCN and GAT. The current version PN should works good for GCN and GAT also (haven't fully tested). Please start from using PN before testing PN-SI and PN-SCS.
For GCN or GAT, now using PN to start.
python main.py --data cora --model DeepGCN --nlayer 10 --missing_rate 100 --norm_mode PN --residual 0
python main.py --data cora --model DeepGAT --nlayer 10 --missing_rate 100 --norm_mode PN --residual 0
cite
If you use our code, please cite
@inproceedings{
zhao2020pairnorm,
title={PairNorm: Tackling Oversmoothing in {\{}GNN{\}}s},
author={Lingxiao Zhao and Leman Akoglu},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=rkecl1rtwB}
}
[email protected]">
14 Sep 10, 2022
380 Nov 24, 2022
99 Dec 19, 2022
1 Dec 18, 2021
6 Nov 04, 2022
3.1k Dec 29, 2022
167 Dec 14, 2022
328 Dec 26, 2022
2 Nov 04, 2022
1.6k Jan 08, 2023
32 Nov 17, 2022
54 Dec 21, 2022
206 Oct 29, 2022
71 Jan 06, 2023
79 Nov 04, 2022
33 Dec 03, 2022
7 Nov 13, 2022
24 Dec 02, 2022
345 Jan 08, 2023
24 Nov 29, 2022