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

A simple implementation of Kalman filter in Multi Object Tracking

WormMovementSimulation - 3D Simulation of Worm Body Movement with Neurons attached to its body

OntoProtein: Protein Pretraining With Ontology Embedding

TimeSHAP explains Recurrent Neural Network predictions.

Effective Use of Transformer Networks for Entity Tracking

Meandering In Networks of Entities to Reach Verisimilar Answers

Prososdy Morph: A python library for manipulating pitch and duration in an algorithmic way, for resynthesizing speech.

Pytorch implementation of Learning with Opponent-Learning Awareness

BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond

SEJE Pytorch implementation

code for our ECCV 2020 paper "A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation"

Source code for the paper "SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text" PACLIC 2021

A Flow-based Generative Network for Speech Synthesis

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

Convert openmmlab (not only mmdetection) series model to tensorrt

Codes for SIGIR'22 Paper 'On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation'

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Runtime type annotations for the shape, dtype etc. of PyTorch Tensors.

This package contains a PyTorch Implementation of IB-GAN of the submitted paper in AAAI 2021