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

Time series annotation library.

GANfolk: Using AI to create portraits of fictional people to sell as NFTs

A simple pygame dino game which can also be trained and played by a NEAT KI

PHOTONAI is a high level python API for designing and optimizing machine learning pipelines.

Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.

Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA results for single-image motion deblurring, image deraining, image denoising (synthetic and real data), and dual-pixel defocus deblurring.

Official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch.

Learning to Map Large-scale Sparse Graphs on Memristive Crossbar

We present a regularized self-labeling approach to improve the generalization and robustness properties of fine-tuning.

[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving

[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features

Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

A denoising diffusion probabilistic model (DDPM) tailored for conditional generation of protein distograms

This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

PaSST: Efficient Training of Audio Transformers with Patchout

3D2Unet: 3D Deformable Unet for Low-Light Video Enhancement (PRCV2021)

A certifiable defense against adversarial examples by training neural networks to be provably robust

This repository lets you interact with Lean through a REPL.

Cowsay - A rewrite of cowsay in python