The official PyTorch implementation for the paper "sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs".

Related tags

Deep Learningpython3pytorchlaplaciangnndigraphs
Overview

Magnetic Graph Convolutional Networks

The Magnetic Eigenmap

A directed 4-cycle

About

The official PyTorch implementation for the paper sMGC: A Complex-Valued Graph Convolutional Network via Magnetic Laplacian for Directed Graphs.

Requirements

To install requirements:

pip3 install -r requirements.txt

Results

Node classification accuracy in Citation networks (%)

Model CoRA CiteSeer PubMed
GAT 82.60 ± 0.40 70.45 ± 0.25 77.45 ± 0.45
sMGC 82.70 ± 0.00 73.30 ± 0.00 79.90 ± 0.10
MGC 82.50 ± 1.00 71.25 ± 0.95 79.70 ± 0.40

Node classification accuracy in WebKB (%)

Model Cornell Texas Washington Wisconsin
GAT 41.03 ± 0.00 52.63 ± 2.63 63.04 ± 0.00 56.61 ± 1.88
sMGC 73.08 ± 1.28 71.05 ± 0.00 68.48 ± 3.26 80.19 ± 2.83
MGC 80.77 ± 3.85 82.90 ± 1.31 70.66 ± 1.08 87.74 ± 2.83

Reproduce experiment results

sMGC

CoRA:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/cora.ini' --alpha=0.03 --t=8.05 --K=38

CiteSeer:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/citeseer.ini' --alpha=0.01 --t=5.16 --K=40

PubMed:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/pubmed.ini' --alpha=0.01 --t=5.95 --K=25

Cornell:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/cornell.ini' --alpha=0.95 --t=45.32 --K=12

Texas:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/texas.ini' --alpha=0.71 --t=45.08 --K=23

Washington:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/washington.ini' --alpha=0.77 --t=45.95 --K=44

Wisconsin:

python3 main_smgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/wisconsin.ini' --alpha=0.93 --t=25.76 --K=34

MGC

CoRA:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/cora.ini' --alpha=0.08 --t=5.85 --K=10 --droprate=0.4

CiteSeer:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/citeseer.ini' --alpha=0.01 --t=25.95 --K=35 --droprate=0.3

PubMed:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/pubmed.ini' --alpha=0.03 --t=15.95 --K=20 --droprate=0.5

Cornell:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/cornell.ini' --alpha=0.66 --t=38.49 --K=31 --droprate=0.6

Texas:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/texas.ini' --alpha=0.75 --t=0.53 --K=4 --droprate=0.5

Washington:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/washington.ini' --alpha=0.73 --t=42.36 --K=21 --droprate=0.1

Wisconsin:

python3 main_mgc.py --mode='test' --seed=100 --dataset_config_path='./config/data/wisconsin.ini' --alpha=0.34 --t=0.52 --K=12 --droprate=0.5
Owner
What we know is a drop. What we do not know is an ocean.
GitHub Repository
MIM: MIM Installs OpenMMLab Packages

MIM provides a unified API for launching and installing OpenMMLab projects and their extensions, and managing the OpenMMLab model zoo.

OpenMMLab 254 Jan 04, 2023
A benchmark dataset for mesh multi-label-classification based on cube engravings introduced in MeshCNN

Double Cube Engravings This script creates a dataset for multi-label mesh clasification, with an intentionally difficult setup for point cloud classif

Yotam Erel 1 Nov 30, 2021
Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution

nnvolterra Run Code Compile first: make compile Run all codes: make all Test xconv: make npxconv_test MNIST dataset needs to be downloaded, converted

1 May 24, 2022
Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology Self-Supervised Vision Transformers Learn Visual Concepts in Histopatholog

Richard Chen 95 Dec 24, 2022
Learning Super-Features for Image Retrieval

Learning Super-Features for Image Retrieval This repository contains the code for running our FIRe model presented in our ICLR'22 paper: @inproceeding

NAVER 101 Dec 28, 2022
Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation

Multi-atlas segmentation (MAS) is a promising framework for medical image segmentation. Generally, MAS methods register multiple atlases, i.e., medical images with corresponding labels, to a target i

NanYoMy 13 Oct 09, 2022
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets This is the official PyTorch implementation for the paper Rapid Neural A

48 Dec 26, 2022
An end-to-end regression problem of predicting the price of properties in Bangalore.

Bangalore-House-Price-Prediction An end-to-end regression problem of predicting the price of properties in Bangalore. Deployed in Heroku using Flask.

Shruti Balan 1 Nov 25, 2022
🔥 Real-time Super Resolution enhancement (4x) with content loss and relativistic adversarial optimization 🔥

🔥 Real-time Super Resolution enhancement (4x) with content loss and relativistic adversarial optimization 🔥

Rishik Mourya 48 Dec 20, 2022
Open source person re-identification library in python

Open-ReID Open-ReID is a lightweight library of person re-identification for research purpose. It aims to provide a uniform interface for different da

Tong Xiao 1.3k Jan 01, 2023
Fast and robust certifiable relative pose estimation

Fast and Robust Relative Pose Estimation for Calibrated Cameras This repository contains the code for the relative pose estimation between two central

42 Dec 06, 2022
Code implementation of "Sparsity Probe: Analysis tool for Deep Learning Models"

Sparsity Probe: Analysis tool for Deep Learning Models This repository is a limited implementation of Sparsity Probe: Analysis tool for Deep Learning

3 Jun 09, 2021
3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.

3D AffordanceNet This repository is the official experiment implementation of 3D AffordanceNet benchmark. 3D AffordanceNet is a 3D point cloud benchma

49 Dec 01, 2022
An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.

CyberBattleSim April 8th, 2021: See the announcement on the Microsoft Security Blog. CyberBattleSim is an experimentation research platform to investi

Microsoft 1.5k Dec 25, 2022
Taichi Course Homework Template

太极图形课S1-标题部分 这个作业未来或将是你的开源项目，标题的内容可以来自作业中的核心关键词，让读者一眼看出你所完成的工作/做出的好玩demo 如果暂时未想好，起名时可以参考“太极图形课S1-xxx作业” 如下是作业（项目）展开说明的方法，可以帮大家理清思路，并且也对读者非常友好，请小伙伴们多多参

TaichiCourse 30 Nov 19, 2022
https://arxiv.org/abs/2102.11005

LogME LogME: Practical Assessment of Pre-trained Models for Transfer Learning How to use Just feed the features f and labels y to the function, and yo

THUML: Machine Learning Group @ THSS 149 Dec 19, 2022
The implementation of 'Image synthesis via semantic composition'.

Image synthesis via semantic synthesis [Project Page] by Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia. Introduction This repository gives

DV Lab 71 Jan 06, 2023
Unsupervised Pre-training for Person Re-identification (LUPerson)

LUPerson Unsupervised Pre-training for Person Re-identification (LUPerson). The repository is for our CVPR2021 paper Unsupervised Pre-training for Per

143 Dec 24, 2022
git《Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser》(2021) GitHub: [fig5]

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser Abstract The success of deep denoisers on real-world colo

Yue Cao 51 Nov 22, 2022
Vision transformers (ViTs) have found only limited practical use in processing images

CXV Convolutional Xformers for Vision Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-o

Cloudwalker 23 Sep 10, 2022