# dsgiitr/graph_nets

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

Repository: https://github.com/dsgiitr/graph_nets
Canonical: https://ross.abutalabs.com/products/dsgiitr-graph_nets
Language: Jupyter Notebook
License Family: other
Topics: graph-representation-learning, graph-convolutional-networks, graph-attention-networks, graph-embedding, deepwalk, node-embedding, graph-sage, chebyshev-polynomials, pytorch
Last push: 2025-03-28T12:24:05+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 13, release rhythm 35, longevity 100
- inputs: {"age_days": 2583, "days_push": 523, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1237, forks 227 (observed 2026-08-28T04:04:05.384857+00:00)

## What it is
A collection of PyTorch implementations with accompanying blog-style Jupyter notebooks explaining major graph representation learning papers: DeepWalk, GCN, GraphSAGE, ChebNet, and GAT. It serves as an educational supplement to the DSG IIT Roorkee blog series 'Explained: Graph Representation Learning'.

## Use cases
- learn graph neural networks with pytorch
- understand how GCN works with code
- implement DeepWalk node embeddings
- study GraphSAGE inductive learning
- tutorial on graph attention networks
- reproduce graph representation learning papers
- learn ChebNet spectral graph convolution

## When to choose
- you want paper implementations paired with intuitive explanations
- you are learning GNNs from scratch with runnable notebooks
- you need reference PyTorch code for classic graph embedding models

## When to avoid
- you need a production-ready or maintained GNN library
- you want a broad API covering many GNN architectures
- you require a licensed dependency for commercial use

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials
- platform: python
- tags: graph-neural-networks, pytorch, node-embeddings, jupyter-notebooks, educational, graph-representation-learning, gcn, graphsage, gat, deepwalk, algorithms

## Member repositories
- dsgiitr/graph_nets (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:05.384857+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:21:51.813182+00:00, confidence not recorded.
  - readme: https://github.com/dsgiitr/graph_nets (fetched 2026-08-28T04:04:05.384857+00:00, sha 8b7e80ec4571)
- Data as of 2026-08-30T08:39:29.467469+00:00.