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}
}
422 Dec 28, 2022
53 Nov 13, 2022
1 Dec 03, 2021
17 Jan 08, 2023
3 Oct 06, 2022
0 Nov 09, 2021
41 Oct 10, 2022
16 Jan 08, 2023
15 Sep 23, 2022
92 Dec 12, 2022
42 Dec 09, 2022
92 Jan 04, 2023
2.6k Jan 04, 2023
99 Jun 28, 2022
55 Dec 28, 2022
19 Dec 10, 2021
305 Dec 21, 2022
55 Dec 06, 2022
3 Jan 03, 2023
2 Oct 20, 2022