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}
}

Source code for PairNorm (ICLR 2020)

Related tags

Overview

PairNorm

usage

update: normalization and PN

cite

Owner

PyTorch Implementation for AAAI'21 "Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection"

A list of awesome PyTorch scholarship articles, guides, blogs, courses and other resources.

Forecasting directional movements of stock prices for intraday trading using LSTM and random forest

PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).

1st Solution For NeurIPS 2021 Competition on ML4CO Dual Task

Install alphafold on the local machine, get out of docker.

PRTR: Pose Recognition with Cascade Transformers

Official Python implementation of the 'Sparse deconvolution'-v0.3.0

A Streamlit component to render ECharts.

Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

DualGAN-tensorflow: tensorflow implementation of DualGAN

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

git《Investigating Loss Functions for Extreme Super-Resolution》(CVPR 2020) GitHub:

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

Official code for: A Probabilistic Hard Attention Model For Sequentially Observed Scenes

VOLO: Vision Outlooker for Visual Recognition

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Some tentative models that incorporate label propagation to graph neural networks for graph representation learning in nodes, links or graphs.

Probabilistic Programming and Statistical Inference in PyTorch

A toolkit for document-level event extraction, containing some SOTA model implementations