HongyangGao / Graph U Nets
Licence: gpl-3.0
Pytorch implementation of Graph U-Nets (ICML19)
Stars: ✭ 300
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Graph U Nets
Pymeasure
Scientific measurement library for instruments, experiments, and live-plotting
Stars: ✭ 255 (-15%)
Mutual labels: graph
Cypher For Gremlin
Cypher for Gremlin adds Cypher support to any Gremlin graph database.
Stars: ✭ 267 (-11%)
Mutual labels: graph
React Flow
Highly customizable library for building interactive node-based UIs, editors, flow charts and diagrams
Stars: ✭ 8,348 (+2682.67%)
Mutual labels: graph
Graph nn
Graph Classification with Graph Convolutional Networks in PyTorch (NeurIPS 2018 Workshop)
Stars: ✭ 268 (-10.67%)
Mutual labels: graph
Javascript Datastructures Algorithms
📚 collection of JavaScript and TypeScript data structures and algorithms for education purposes. Source code bundle of JavaScript algorithms and data structures book
Stars: ✭ 3,221 (+973.67%)
Mutual labels: graph
Bitmeteros
BitMeter OS - a cross-platform bandwidth monitor
Stars: ✭ 266 (-11.33%)
Mutual labels: graph
Graph Based Deep Learning Literature
links to conference publications in graph-based deep learning
Stars: ✭ 3,428 (+1042.67%)
Mutual labels: graph
Sparklinelayout
Simple and lightweight library for drawing sparklines / graphs. Support markers and gradients.
Stars: ✭ 291 (-3%)
Mutual labels: graph
Data Structures Algorithms
My implementation of 85+ popular data structures and algorithms and interview questions in Python 3 and C++
Stars: ✭ 273 (-9%)
Mutual labels: graph
Memstate
In-memory event-sourced ACID-transactional distributed object graph engine for .NET Standard
Stars: ✭ 280 (-6.67%)
Mutual labels: graph
Struc2vec
This repository provides a reference implementation of struc2vec.
Stars: ✭ 291 (-3%)
Mutual labels: graph
Rgl
RGL is a framework for graph data structures and algorithms in Ruby.
Stars: ✭ 279 (-7%)
Mutual labels: graph
PyTorch Implementation of Graph U-Nets
Created by Hongyang Gao @ Iowa State University, and Shuiwang Ji @ Texas A&M University.
About
PyTorch implementation of Graph U-Nets. Check http://proceedings.mlr.press/v97/gao19a/gao19a.pdf for more information.
Methods
Graph Pooling Layer
Graph Unpooling Layer
Graph U-Net
Installation
Type
./run_GNN.sh DATA FOLD GPU
to run on dataset using fold number (1-10).
You can run
./run_GNN.sh DD 0 0
to run on DD dataset with 10-fold cross validation on GPU #0.
Code
The detail implementation of Graph U-Net is in src/utils/ops.py.
Datasets
Check the "data/README.md" for the format.
Results
| Models | DD | IMDBMULTI | PROTEINS |
|---|---|---|---|
| PSCN | 76.3 ± 2.6% | 45.2 ± 2.8% | 75.9 ± 2.8% |
| DIFFPOOL | 80.6% | - | 76.3% |
| SAGPool | 76.5% | - | 71.9% |
| GIN | 82.0 ± 2.7% | 52.3 ± 2.8% | 76.2 ± 2.8% |
| g-U-Net | 83.0 ± 2.2% | 56.7 ± 2.9% | 78.7 ± 4.2% |
Reference
If you find the code useful, please cite our paper:
@inproceedings{gao2019graph,
title={Graph U-Nets},
author={Gao, Hongyang and Ji, Shuiwang},
booktitle={International Conference on Machine Learning},
pages={2083--2092},
year={2019}
}
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].