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}
}
52 Oct 31, 2022
1.1k Jan 03, 2023
223 Oct 18, 2022
2 Dec 12, 2022
2 Feb 02, 2022
8 Jul 16, 2022
4 Nov 15, 2022
52 Dec 05, 2022
83 Dec 30, 2022
165 Nov 04, 2022
32 Dec 30, 2022
18 Nov 18, 2022
44 Dec 30, 2022
111 Dec 18, 2022
28 Dec 28, 2022
68 Jan 04, 2023
2 Oct 11, 2022
2.2k Jan 01, 2023
8 Aug 31, 2022
17 Dec 04, 2022