Skip to content

Utah-Math-Data-Science/PR-inspired-aggregation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Douglas-Rachford Graph Neural Network

This repository is the official PyTorch implementation of "Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs."

Installation

Dockerfile: Recommended install using Dockerfile.drgnn.

Manual: Alternatively use pip3 install -r requirements.txt to manually install.

Usage

agg: The ./agg/ directory contains all the relevant code for DRGNN.

tasks: Individual tasks are located in the ./tasks/ directory with .py driver files and .yaml settings files.

python3 ./tasks/arxiv.py

sweeps: Sweep results are run using wandb and can be easily instantiated and run by performing the following:

  1. Move desired runs to ./sweeps/todo/.
	mv ./sweeps/tables/* ./sweeps/todo/
  1. Generate sweep_ids.log.
	bash ./sweeps/generate.sh todo
  1. Run the sweep.
	bash ./sweeps/run.sh <device>

analysis: All other results are found in the ./analysis/ directory.

baselines: All baseline codes can be found in the ./baselines/ directory.

Citation

Awaiting publication.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published