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

Code for the Active Speakers in Context Paper (CVPR2020)

SOLOv2 on onnx & tensorRT

Official repository for Natural Image Matting via Guided Contextual Attention

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains (IJCV submission)

An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax

This is a five-step framework for the development of intrusion detection systems (IDS) using machine learning (ML) considering model realization, and performance evaluation.

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

Implementation of the Triangle Multiplicative module, used in Alphafold2 as an efficient way to mix rows or columns of a 2d feature map, as a standalone package for Pytorch

Lightweight Python library for adding real-time object tracking to any detector.

Security evaluation module with onnx, pytorch, and SecML.

Latex code for making neural networks diagrams

dualPC.R contains the R code for the main functions.

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations

Blind Video Temporal Consistency via Deep Video Prior

This repo uses a combination of logits and feature distillation method to teach the PSPNet model of ResNet18 backbone with the PSPNet model of ResNet50 backbone. All the models are trained and tested on the PASCAL-VOC2012 dataset.

Navigating StyleGAN2 w latent space using CLIP

Catch-all collection of generative art made using processing

Repository accompanying the "Sign Pose-based Transformer for Word-level Sign Language Recognition" paper

Jupyter Dock is a set of Jupyter Notebooks for performing molecular docking protocols interactively, as well as visualizing, converting file formats and analyzing the results.