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

Open-CyKG: An Open Cyber Threat Intelligence Knowledge Graph

Direct design of biquad filter cascades with deep learning by sampling random polynomials.

一个目标检测的通用框架(不需要cuda编译)，支持Yolo全系列(v2~v5)、EfficientDet、RetinaNet、Cascade-RCNN等SOTA网络。

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

SpeechBrain is an open-source and all-in-one speech toolkit based on PyTorch.

Patch-Diffusion Code (AAAI2022)

Code for the prototype tool in our paper "CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning".

Like ThreeJS but for Python and based on wgpu

Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-local Spatial-Temporal Similarity

Interpolation-based reduced-order models

A Number Recognition algorithm

HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset (ICCV 2021)

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Sionna: An Open-Source Library for Next-Generation Physical Layer Research

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Dataset for the Research2Clinics @ NeurIPS 2021 Paper: What Do You See in this Patient? Behavioral Testing of Clinical NLP Models

Code for the Paper "Diffusion Models for Handwriting Generation"

Use AI to generate a optimized stock portfolio

An Open-Source Toolkit for Prompt-Learning.

Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)