THUDM / Grand
Licence: mit
Source code and dataset of the NeurIPS 2020 paper "Graph Random Neural Network for Semi-Supervised Learning on Graphs"
Stars: ✭ 75
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Grand
semantic-parsing-dual
Source code and data for ACL 2019 Long Paper ``Semantic Parsing with Dual Learning".
Stars: ✭ 17 (-77.33%)
Mutual labels: semi-supervised-learning, data-augmentation
Stylealign
[ICCV 2019]Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Transition
Stars: ✭ 172 (+129.33%)
Mutual labels: data-augmentation, semi-supervised-learning
Pedestrian Synthesis Gan
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
Stars: ✭ 73 (-2.67%)
Mutual labels: data-augmentation
Daru View
daru-view is for easy and interactive plotting in web application & IRuby notebook. daru-view is a plugin gem to the existing daru gem.
Stars: ✭ 65 (-13.33%)
Mutual labels: graphs
Doccreator
DIAR software for synthetic document image and groundtruth generation, with various degradation models for data augmentation
Stars: ✭ 60 (-20%)
Mutual labels: data-augmentation
Evalne
Source code for EvalNE, a Python library for evaluating Network Embedding methods.
Stars: ✭ 67 (-10.67%)
Mutual labels: graphs
Acgan Pytorch
Pytorch implementation of Conditional Image Synthesis with Auxiliary Classifier GANs
Stars: ✭ 57 (-24%)
Mutual labels: semi-supervised-learning
Vscode Vega Viewer
VSCode extension for Interactive Preview of Vega & Vega-Lite maps 🗺️ & graphs 📈
Stars: ✭ 75 (+0%)
Mutual labels: graphs
Data generator object detection 2d
A data generator for 2D object detection
Stars: ✭ 73 (-2.67%)
Mutual labels: data-augmentation
Mean Teacher
A state-of-the-art semi-supervised method for image recognition
Stars: ✭ 1,130 (+1406.67%)
Mutual labels: semi-supervised-learning
Cnn graph
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Stars: ✭ 1,110 (+1380%)
Mutual labels: graphs
Sparsely Grouped Gan
Code for paper "Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation"
Stars: ✭ 68 (-9.33%)
Mutual labels: semi-supervised-learning
Lgenerics
Generic algorithms and data structures for Lazarus/Free Pascal
Stars: ✭ 59 (-21.33%)
Mutual labels: graphs
Pymarketcap
Python3 API wrapper and web scraper for https://coinmarketcap.com
Stars: ✭ 73 (-2.67%)
Mutual labels: graphs
Dips
NAACL 2019: Submodular optimization-based diverse paraphrasing and its effectiveness in data augmentation
Stars: ✭ 59 (-21.33%)
Mutual labels: data-augmentation
Ntds 2017
Material for the EPFL master course "A Network Tour of Data Science", edition 2017.
Stars: ✭ 61 (-18.67%)
Mutual labels: graphs
Graphia
A visualisation tool for the creation and analysis of graphs
Stars: ✭ 67 (-10.67%)
Mutual labels: graphs
Deepaffinity
Protein-compound affinity prediction through unified RNN-CNN
Stars: ✭ 75 (+0%)
Mutual labels: semi-supervised-learning
GRAND
This is the code of paper: Graph Random Neural Network for Semi-Supervised Learning on Graphs [arxiv]
Please cite our paper if you think our work is helpful to you:
@inproceedings{feng2020grand,
title={Graph Random Neural Network for Semi-Supervised Learning on Graphs},
author={Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang},
booktitle={NeurIPS'20},
year={2020}
}
Requirements
- Python 3.7.3
- Please install other pakeages by
pip install -r requirements.txt
Usage Example
- Running one trial on Cora:
sh run_cora.sh
- Running 100 trials with random initializations on Cora:
sh run100_cora.sh
- Calculating the average accuracy of 100 trails on Cora:
python result_100run.py cora
Results
Our model achieves the following accuracies on Cora, CiteSeer and Pubmed with the public splits:
Model name | Cora | CiteSeer | Pubmed |
---|---|---|---|
GRAND | 85.4% | 75.4% | 82.7% |
Running Environment
The experimental results reported in paper are conducted on a single NVIDIA GeForce RTX 2080 Ti with CUDA 10.0, which might be slightly inconsistent with the results induced by other platforms.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].