A Graph Neural Network Tool for Recovering Dense Sub-graphs in Random Dense Graphs.

Related tags

Deep Learning PYGON
Overview

PYGON

A Graph Neural Network Tool for Recovering Dense Sub-graphs in Random Dense Graphs.

Installation

This code requires to install and run the graph-measures package. Currently, we have a copy of this package that is ready to use (in "graph_calculations" directory), but it is possible to remove its content, download the graph_measures repository and follow the instructions below to be able to run this code. The conda environment for this project (part 2 in the instructions) is still required.
A detailed explanation for graph-measures package appears in a manual in graph-measures repository. Here we present short instructions:

  1. Download the graph-measures project into "graph_calculations/graph_measures".
  2. Create the anaconda environment for running this project by running conda env create -f env.yml in the terminal.
  3. Activate the new environment: conda activate boost.
  4. Move into the directory "graph_calculations/graph_measures/features_algorithms/accelerated_graph_features/src".
  5. Make the feature calculation files for motif calculations: make -f Makefile-gpu.
  6. Great! Now one should be able to run PYGON end-to-end. Remember to work in boost environment when using this code.

Note that this code was tested only on Unix machines with GPUs. Some feature calculations might not work in other machines.
Note also that the virtual environment we tried is anaconda-based.

How to Use

  • The main code directory is "model". The other directory includes the code for feature calculations and will include saved pickle files of graphs and their features.

  • For simply trying the PYGON model, one can run python pygon_main.py in a terminal. This will run a simple training of PYGON on G(500, 0.5, 20) graphs (which will be built and dumped in "graph_calculations/pkl"). One can change the parameters or graph specifications appearing there to try PYGON on graphs of other sizes, edge probabilities, planted sub-graph sizes, planted sub-graph types or model hyper-parameters.

  • More detailed performance tests can be found in performance_testing.py.

  • To run an NNI experiment on the performance of PYGON, move into "to_run_nni" and run the configuration the experiment as guided in NNI's documentation.

  • The existing algorithms to which we compared our performance, as well as a faster version of PYGON (without dumping or printing anything), can be found in other_algorithms.py.

  • The cleaning stage using the cleaning algorithm can be found in second_stage.py.

You might also like...
This repo is about implementing different approaches of pose estimation and also is a sub-task of the smart hospital bed project :smile:

Pose-Estimation This repo is a sub-task of the smart hospital bed project which is about implementing the task of pose estimation 😄 Many thanks to th

Max 11 Oct 17, 2022
The implementation of
The implementation of "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Band Speech Enhancement"

SF-Net for fullband SE This is the repo of the manuscript "Optimizing Shoulder to Shoulder: A Coordinated Sub-Band Fusion Model for Real-Time Full-Ban

Guochen Yu 36 Dec 2, 2022
This is a model made out of Neural Network specifically a Convolutional Neural Network model
This is a model made out of Neural Network specifically a Convolutional Neural Network model

This is a model made out of Neural Network specifically a Convolutional Neural Network model. This was done with a pre-built dataset from the tensorflow and keras packages. There are other alternative libraries that can be used for this purpose, one of which is the PyTorch library.

null 9 Oct 18, 2022
This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

The Neural Process Family This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CN

DeepMind 892 Dec 28, 2022
We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

Deep GNN, Shallow Sampling Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, R

Facebook Research 117 Dec 20, 2022
A static analysis library for computing graph representations of Python programs suitable for use with graph neural networks.

python_graphs This package is for computing graph representations of Python programs for machine learning applications. It includes the following modu

Google Research 258 Dec 29, 2022
The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"

GSDN-F and GSDN-EF This repository provides a reference implementation of GSDN-F and GSDN-EF as described in the paper "Understanding Graph Neural Net

Guoji Fu 18 Nov 14, 2022
On Size-Oriented Long-Tailed Graph Classification of Graph Neural Networks

On Size-Oriented Long-Tailed Graph Classification of Graph Neural Networks We provide the code (in PyTorch) and datasets for our paper "On Size-Orient

Zemin Liu 4 Jun 18, 2022
Graph neural network message passing reframed as a Transformer with local attention

Adjacent Attention Network An implementation of a simple transformer that is equivalent to graph neural network where the message passing is done with

Phil Wang 49 Dec 28, 2022
Comments
  • Update env.yml

    Update env.yml

    Hi. After trying to run PYGON, I found out that the environment building file has way too many unnecessary dependencies (which are in fact sub-dependencies). I removed them from the YAML file.

    opened by itayl13 0
Owner
Yoram Louzoun's Lab
Yoram Louzoun's Lab
GitHub
Some tentative models that incorporate label propagation to graph neural networks for graph representation learning in nodes, links or graphs.

Some tentative models that incorporate label propagation to graph neural networks for graph representation learning in nodes, links or graphs.

zshicode 1 Nov 18, 2021
Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning

Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning This repository is official Tensorflow implementation of paper: Ensemb

Seunghyun Lee 12 Oct 18, 2022
This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch.

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch.

BUPT GAMMA Lab 519 Jan 2, 2023
Random-Afg - Afghanistan Random Old Idz Cloner Tools

AFGHANISTAN RANDOM OLD IDZ CLONER TOOLS Install $ apt update $ apt upgrade $ apt

MAHADI HASAN AFRIDI 5 Jan 26, 2022
Random Walk Graph Neural Networks

Random Walk Graph Neural Networks This repository is the official implementation of Random Walk Graph Neural Networks. Requirements Code is written in

Giannis Nikolentzos 38 Jan 2, 2023
ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representa

Bats Research 94 Nov 21, 2022
Scalable Graph Neural Networks for Heterogeneous Graphs

Neighbor Averaging over Relation Subgraphs (NARS) NARS is an algorithm for node classification on heterogeneous graphs, based on scalable neighbor ave

Facebook Research 67 Dec 3, 2022
PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement."

FullSubNet This Git repository for the official PyTorch implementation of "A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech E

郝翔 357 Jan 4, 2023
Code and data of the Fine-Grained R2R Dataset proposed in paper Sub-Instruction Aware Vision-and-Language Navigation

Fine-Grained R2R Code and data of the Fine-Grained R2R Dataset proposed in the EMNLP2020 paper Sub-Instruction Aware Vision-and-Language Navigation. C

YicongHong 34 Nov 15, 2022
Sub-Cluster AdaCos: Learning Representations for Anomalous Sound Detection.

Accompanying code for the paper Sub-Cluster AdaCos: Learning Representations for Anomalous Sound Detection.

Kevin Wilkinghoff 6 Dec 1, 2022