https://github.com/twjiang/graphSAGE-pytorch

A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE.
https://github.com/twjiang/graphSAGE-pytorch

Last synced: 6 days ago
JSON representation

A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE.

• Host: GitHub
• URL: https://github.com/twjiang/graphSAGE-pytorch
• Owner: twjiang
• Created: 2019-03-22T05:59:22.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-10-03T23:07:29.000Z (9 months ago)
• Last Synced: 2024-03-22T16:35:41.568Z (3 months ago)
• Language: Python
• Homepage:
• Size: 18.1 MB
• Stars: 576
• Watchers: 10
• Forks: 144
• Open Issues: 13
• Metadata Files:
  • Readme: README.md

Lists

• awesome-stars - twjiang/graphSAGE-pytorch - A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE. (Python)

README

        
## A PyTorch implementation of GraphSAGE

This package contains a PyTorch implementation of [GraphSAGE](http://snap.stanford.edu/graphsage/).

#### Authors of this code package: 

[Tianwen Jiang](https://github.com/twjiang) ([email protected]), 

[Tong Zhao](https://github.com/zhao-tong) ([email protected]),

[Daheng Wang](https://github.com/adamwang0705) ([email protected]).

## Environment settings

- python==3.6.8

- pytorch==1.0.0

## Basic Usage

**Main Parameters:**

```

--dataSet     The input graph dataset. (default: cora)

--agg_func    The aggregate function. (default: Mean aggregater)

--epochs      Number of epochs. (default: 50)

--b_sz        Batch size. (default: 20)

--seed        Random seed. (default: 824)

--unsup_loss  The loss function for unsupervised learning. ('margin' or 'normal', default: normal)

--config      Config file. (default: ./src/experiments.conf)

--cuda        Use GPU if declared.

```

**Learning Method**

The user can specify a learning method by --learn_method, 'sup' is for supervised learning, 'unsup' is for unsupervised learning, and 'plus_unsup' is for jointly learning the loss of supervised and unsupervised method.

**Example Usage**

To run the unsupervised model on Cuda:

```

python -m src.main --epochs 50 --cuda --learn_method unsup

```