Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/dsgiitr/graph_nets

PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT.
https://github.com/dsgiitr/graph_nets

chebyshev-polynomials deepwalk graph-attention-networks graph-convolutional-networks graph-embedding graph-representation-learning graph-sage node-embedding pytorch

Last synced: 2 days ago
JSON representation

PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT.

Awesome Lists containing this project

README 

        
 Graph Representation Learning 






This repo is a supplement to our blog series *Explained: Graph Representation Learning*. The following major papers and corresponding blogs have been covered as part of the series and we look to add blogs on a few other significant works in the field.



 Setup 



Clone the git repository :



```

git clone https://github.com/dsgiitr/graph_nets.git

```



Python 3 with Pytorch 1.3.0 are the primary requirements. The `requirements.txt` file contains a listing of other dependencies. To install all the requirements, run the following:



`pip install -r requirements.txt`



 1. Understanding DeepWalk 





Unsupervised online learning approach, inspired from word2vec in NLP, but, here the goal is to generate node embeddings.

- [DeepWalk Blog](https://dsgiitr.com/blogs/deepwalk)

- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/DeepWalk/DeepWalk_Blog%2BCode.ipynb)

- [Code](https://github.com/dsgiitr/graph_nets/blob/master/DeepWalk/DeepWalk.py)

- [Paper -> DeepWalk: Online Learning of Social Representations](https://arxiv.org/abs/1403.6652)



 2. A Review : Graph Convolutional Networks (GCN) 





GCNs draw on the idea of Convolution Neural Networks re-defining them for the non-euclidean data domain. They are  convolutional, because filter parameters are typically shared over all locations in the graph unlike typical GNNs. 

- [GCN Blog](https://dsgiitr.com/blogs/gcn)

- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GCN/GCN_Blog%2BCode.ipynb)

- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GCN/GCN.py)

- [Paper -> Semi-Supervised Classification with Graph Convolutional Networks](https://arxiv.org/abs/1609.02907)



 3. Graph SAGE(SAmple and aggreGatE) 





Previous approaches are transductive and don't naturally generalize to unseen nodes. GraphSAGE is an inductive framework leveraging node feature information to efficiently generate node embeddings.

- [GraphSAGE Blog](https://dsgiitr.com/blogs/graphsage)

- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GraphSAGE/GraphSAGE_Code%2BBlog.ipynb)

- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GraphSAGE/GraphSAGE.py)

- [Paper -> Inductive Representation Learning on Large Graphs](https://arxiv.org/abs/1706.02216)



 4. ChebNet: CNN on Graphs with Fast Localized Spectral Filtering 





ChebNet is a formulation of CNNs in the context of spectral graph theory.

- [ChebNet Blog](https://dsgiitr.com/blogs/chebnet/)

- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/ChebNet/Chebnet_Blog%2BCode.ipynb)

- [Code](https://github.com/dsgiitr/graph_nets/blob/master/ChebNet/coarsening.py)

- [Paper -> Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://arxiv.org/abs/1606.09375)







 5. Understanding Graph Attention Networks 





GAT is able to attend over their neighborhoods’ features, implicitly specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation or depending on knowing the graph structure upfront.

- [GAT Blog](https://dsgiitr.com/blogs/gat)

- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GAT/GAT_Blog%2BCode.ipynb)

- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GAT/GAT_PyG.py)

- [Paper -> Graph Attention Networks](https://arxiv.org/abs/1710.10903)







## Citation



Please use the following entry for citing the blog.

```

@misc{graph_nets,

  author = {A. Dagar and A. Pant and S. Gupta and S. Chandel},

  title = {graph_nets},

  year = {2020},

  publisher = {GitHub},

  journal = {GitHub repository},

  howpublished = {\url{https://github.com/dsgiitr/graph_nets}},

}

```