{"id":13687856,"url":"https://github.com/dsgiitr/graph_nets","last_synced_at":"2025-05-14T18:06:32.108Z","repository":{"id":37698892,"uuid":"201037432","full_name":"dsgiitr/graph_nets","owner":"dsgiitr","description":"PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet \u0026 GAT.","archived":false,"fork":false,"pushed_at":"2025-03-28T12:24:05.000Z","size":11637,"stargazers_count":1180,"open_issues_count":3,"forks_count":227,"subscribers_count":36,"default_branch":"master","last_synced_at":"2025-04-08T19:23:41.625Z","etag":null,"topics":["chebyshev-polynomials","deepwalk","graph-attention-networks","graph-convolutional-networks","graph-embedding","graph-representation-learning","graph-sage","node-embedding","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dsgiitr.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-08-07T11:33:14.000Z","updated_at":"2025-04-06T12:50:40.000Z","dependencies_parsed_at":"2022-09-02T07:12:31.193Z","dependency_job_id":"982c6ca6-acbd-473a-9227-0f9e9728e462","html_url":"https://github.com/dsgiitr/graph_nets","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsgiitr%2Fgraph_nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsgiitr%2Fgraph_nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsgiitr%2Fgraph_nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dsgiitr%2Fgraph_nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dsgiitr","download_url":"https://codeload.github.com/dsgiitr/graph_nets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254198514,"owners_count":22030965,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chebyshev-polynomials","deepwalk","graph-attention-networks","graph-convolutional-networks","graph-embedding","graph-representation-learning","graph-sage","node-embedding","pytorch"],"created_at":"2024-08-02T15:01:02.020Z","updated_at":"2025-05-14T18:06:27.100Z","avatar_url":"https://github.com/dsgiitr.png","language":"Jupyter Notebook","readme":"\u003ch1 align=\"center\"\u003e Graph Representation Learning \u003c/h1\u003e\n\n\u003cimg align=\"center\" src=\"https://dsgiitr.in/images/work/graph_nets.svg\"\u003e\n\nThis 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.\n\n\n\u003ch2\u003e Setup \u003c/h2\u003e\n\nClone the git repository :\n\n```\ngit clone https://github.com/dsgiitr/graph_nets.git\n```\n\nPython 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:\n\n`pip install -r requirements.txt`\n\n\u003ch2 align=\"center\"\u003e 1. Understanding DeepWalk \u003c/h2\u003e\n\u003cimg align=\"right\" width=\"500x\" height=\"120x\" src=\"https://miro.medium.com/max/4005/1*j-P55wBp5PP9oqrxDxdDpw.png\"\u003e\n\nUnsupervised online learning approach, inspired from word2vec in NLP, but, here the goal is to generate node embeddings.\n- [DeepWalk Blog](https://dsgiitr.in/blogs/deepwalk)\n- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/DeepWalk/DeepWalk_Blog%2BCode.ipynb)\n- [Code](https://github.com/dsgiitr/graph_nets/blob/master/DeepWalk/DeepWalk.py)\n- [Paper -\u003e DeepWalk: Online Learning of Social Representations](https://arxiv.org/abs/1403.6652)\n\n\n\u003ch2 align=\"center\"\u003e 2. A Review : Graph Convolutional Networks (GCN) \u003c/h2\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"/GCN/img/gcn_architecture.png\"\u003e\n\nGCNs 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. \n- [GCN Blog](https://dsgiitr.in/blogs/gcn)\n- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GCN/GCN_Blog%2BCode.ipynb)\n- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GCN/GCN.py)\n- [Paper -\u003e Semi-Supervised Classification with Graph Convolutional Networks](https://arxiv.org/abs/1609.02907)\n\n\n\u003ch2 align=\"center\"\u003e 3. Graph SAGE(SAmple and aggreGatE) \u003c/h2\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"/GraphSAGE/img/GraphSAGE_cover.jpg\"\u003e\n\nPrevious 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.\n- [GraphSAGE Blog](https://dsgiitr.in/blogs/graphsage)\n- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GraphSAGE/GraphSAGE_Code%2BBlog.ipynb)\n- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GraphSAGE/GraphSAGE.py)\n- [Paper -\u003e Inductive Representation Learning on Large Graphs](https://arxiv.org/abs/1706.02216)\n\n\n\u003ch2 align=\"center\"\u003e 4. ChebNet: CNN on Graphs with Fast Localized Spectral Filtering \u003c/h2\u003e\n\u003cimg align=\"right\" width=\"600x\" src=\"https://i.ibb.co/QcfhJRJ/Screenshot-2020-09-17-at-6-50-27-AM.jpg\"\u003e\n\nChebNet is a formulation of CNNs in the context of spectral graph theory.\n- [ChebNet Blog](https://dsgiitr.in/blogs/chebnet/)\n- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/ChebNet/Chebnet_Blog%2BCode.ipynb)\n- [Code](https://github.com/dsgiitr/graph_nets/blob/master/ChebNet/coarsening.py)\n- [Paper -\u003e Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://arxiv.org/abs/1606.09375)\n\n\u003cbr/\u003e\n\n\u003ch2 align=\"center\"\u003e 5. Understanding Graph Attention Networks \u003c/h2\u003e\n\u003cimg align=\"right\" width=\"500x\" src=\"/GAT/img/GAT_Cover.jpg\"\u003e\n\nGAT 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.\n- [GAT Blog](https://dsgiitr.in/blogs/gat)\n- [Jupyter Notebook](https://github.com/dsgiitr/graph_nets/blob/master/GAT/GAT_Blog%2BCode.ipynb)\n- [Code](https://github.com/dsgiitr/graph_nets/blob/master/GAT/GAT_PyG.py)\n- [Paper -\u003e Graph Attention Networks](https://arxiv.org/abs/1710.10903)\n\n\u003cbr/\u003e\n\n## Citation\n\nPlease use the following entry for citing the blog.\n```\n@misc{graph_nets,\n  author = {A. Dagar and A. Pant and S. Gupta and S. Chandel},\n  title = {graph_nets},\n  year = {2020},\n  publisher = {GitHub},\n  journal = {GitHub repository},\n  howpublished = {\\url{https://github.com/dsgiitr/graph_nets}},\n}\n```\n","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsgiitr%2Fgraph_nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdsgiitr%2Fgraph_nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsgiitr%2Fgraph_nets/lists"}