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

Latent Execution for Neural Program Synthesis

Angle data is a simple data type.

Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling"

Gif-caption - A straightforward GIF Captioner written in Python

ReferFormer - Official Implementation of ReferFormer

TAUFE: Task-Agnostic Undesirable Feature DeactivationUsing Out-of-Distribution Data

Neural Cellular Automata + CLIP

Milano is a tool for automating hyper-parameters search for your models on a backend of your choice.

Code of paper Interact, Embed, and EnlargE (IEEE): Boosting Modality-specific Representations for Multi-Modal Person Re-identification.

Misc YOLOL scripts for use in the Starbase space sandbox videogame

CNNs for Sentence Classification in PyTorch

Paper Code：A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection

Python Library for learning (Structure and Parameter) and inference (Statistical and Causal) in Bayesian Networks.

Official implementation of "Learning Proposals for Practical Energy-Based Regression", 2021.

Api's bulid in Flask perfom to manage Todo Task.

Self-Supervised Learning with Kernel Dependence Maximization

Zero-Shot Text-to-Image Generation VQGAN+CLIP Dockerized

General Vision Benchmark, a project from OpenGVLab

A new GCN model for Point Cloud Analyse

POCO: Point Convolution for Surface Reconstruction