DGN - GitLite

KO | EN

gitlite — search

#hacktoberfest #typescript #go #machine-learning #rust #deep-learning #nodejs #kubernetes #vue #security #ios #mcp #openai #open-source

DGN

(★ 117)

Implementation of Directional Graph Networks in PyTorch and DGL

파일 탐색기

최종 버전 다운로드 (.zip)

- - aggregators.py
  - dgn_layer.py
  - scalers.py
- - aggregators.py
  - dgn_layer.py
  - eigen_agg.py
  - scalers.py
- layers.py
- - molecules_graph_classification_DGN_HIV.json
  - molecules_graph_classification_DGN_PCBA.json
  - molecules_graph_regression_DGN_ZINC.json
  - SBMs_node_clustering_DGN_PATTERN.json
  - superpixels_graph_classification_DGN_CIFAR10.json
- - download_datasets.sh
  - HIV.py
  - molecules.py
  - multiplicity_eig.py
  - PCBA.py
  - README.md
  - SBMs.py
  - superpixels.py
- - setup.md
- - comparison_table.png
  - full-method.png
  - results_table.png
- - aggregators.py
  - dgn_layer.py
  - layers.py
  - mlp_readout_layer.py
  - scalers.py
- - metrics.py
  - train_COLLAB_edge_classification.py
  - train_HIV_graph_classification.py
  - train_molecules_graph_regression.py
  - train_PCBA_graph_classification.py
  - train_SBMs_node_classification.py
  - train_superpixels_graph_classification.py
- environment_cpu.yml
- environment_gpu.yml
- main_HIV.py
- main_molecules.py
- main_PCBA.py
- main_SBMs_node_classification.py
- main_superpixels.py
- README.md
- requirements.txt
.gitignore
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/Saro00/DGN

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd DGN

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r realworld_benchmark/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Directional Graph Networks

Implementation of Directional Graph Networks in PyTorch and DGL.

![method](https://raw.githubusercontent.com/Saro00/DGN/master/realworld_benchmark/images/full-method.png)

## Overview

We provide the implementation of the Directional Graph Networks (DGN) in PyTorch and DGL frameworks, along with scripts for running real-world benchmarks. The repository is organised as follows:

- `models` contains:
  - `pytorch` contains the various GNN models implemented in PyTorch: the implementation of the aggregators, the scalers, the DGN layer and the directional aggregation matrix (`eigen_agg`).
  - `dgl` contains the DGN model implemented via the [DGL library](https://www.dgl.ai/): aggregators, scalers, and DGN layer.
  - `layers.py` contains general NN layers used by the various models
- `realworld_benchmark` contains various scripts from [Benchmarking GNNs](https://github.com/graphdeeplearning/benchmarking-gnns) 
and [Open Graph Benchmark](https://ogb.stanford.edu/) to download the real-world benchmarks and train the DGN on them. 
In `realworld_benchmark/README.md` we provide instructions for runnning the experiments.

## Reference
```
@article{beaini2020directional,
  title={Directional graph networks},
  author={Beaini, Dominique and Passaro, Saro and L{\'e}tourneau, Vincent and Hamilton, William L and Corso, Gabriele and Li{\`o}, Pietro},
  journal={arXiv preprint arXiv:2010.02863},
  year={2020}
}
```

## License
MIT