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

Toward Spatially Unbiased Generative Models (ICCV 2021)

Coursera - Quiz & Assignment of Coursera

Learning multiple gaits of quadruped robot using hierarchical reinforcement learning

Generative Art Using Neural Visual Grammars and Dual Encoders

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

MOT-Tracking-by-Detection-Pipeline - For Tracking-by-Detection format MOT (Multi Object Tracking), is it a framework that separates Detection and Tracking processes?

Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561

Converts geometry node attributes to built-in attributes

HMLLDB is a collection of LLDB commands to assist in the debugging of iOS apps.

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Creating multimodal multitask models

Code for the paper "Location-aware Single Image Reflection Removal"

Hashformers is a framework for hashtag segmentation with transformers.

Multi-task Self-supervised Object Detection via Recycling of Bounding Box Annotations (CVPR, 2019)

A framework that allows people to write their own Rocket League bots.

A Distributional Approach To Controlled Text Generation

Code to accompany the paper "Finding Bipartite Components in Hypergraphs", which is published in NeurIPS'21.

Paddle pit - Rethinking Spatial Dimensions of Vision Transformers

Applying curriculum to meta-learning for few shot classification

The Official Repository for "Generalized OOD Detection: A Survey"