# microsoft/gated-graph-neural-network-samples

Sample Code for Gated Graph Neural Networks

Repository: https://github.com/microsoft/gated-graph-neural-network-samples
Canonical: https://ross.abutalabs.com/products/gated-graph-neural-network-samples
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2019-10-10T09:27:16+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3215, "days_push": 2519, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1029, forks 255 (observed 2026-08-28T04:03:17.630718+00:00)

## What it is
Sample implementations of Gated Graph Neural Networks (GGNN) and Graph Convolutional Networks in TensorFlow, applied to learning properties of chemical molecules. It includes dense, sparse, and asynchronous GNN variants, and is no longer maintained in favor of microsoft/tf-gnn-samples.

## Use cases
- learn how to implement gated graph neural networks
- train a GNN to predict chemical molecule properties
- compare dense vs sparse graph neural network implementations
- run graph convolutional networks on molecular data
- study asynchronous message passing in graph neural networks

## When to choose
- you want reference sample code for GGNNs in TensorFlow 1.x
- you are studying molecular property prediction with GNNs
- you need a starting point for dense or sparse GNN implementations

## When to avoid
- you need maintained or up-to-date GNN code - use microsoft/tf-gnn-samples instead
- you use modern TensorFlow or PyTorch versions
- you need production-ready GNN libraries

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, chemistry
- platform: python
- tags: graph-neural-networks, tensorflow, sample-code, ggnn, graph-convolutional-networks, molecular-property-prediction

## Member repositories
- microsoft/gated-graph-neural-network-samples (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.630718+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 2026-08-30T07:07:39.962881+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/gated-graph-neural-network-samples (fetched 2026-08-28T04:03:17.630718+00:00, sha 489d7ea0936d)
- Data as of 2026-08-30T08:39:29.467469+00:00.