Graph Convolutional Networks

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7406 stars · 1997 forks observed · 2026-10-01

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A TensorFlow implementation of Graph Convolutional Networks (GCN) for semi-supervised node classification on graphs, accompanying the ICLR 2017 paper by Kipf and Welling. It includes demo training scripts, citation network datasets (Cora, Citeseer, Pubmed), and support for graph-level classification with pooling.

Use cases

• classify nodes in a graph with a graph convolutional network
• reproduce the GCN paper results on Cora, Citeseer, or Pubmed
• run semi-supervised learning on citation networks
• experiment with Chebyshev polynomial graph convolutions
• perform batch-wise classification of multiple graph instances
• learn how GCNs work with a reference implementation

When to choose

• you need the canonical reference implementation of the original GCN paper
• you work with TensorFlow and want node classification on graphs
• you want a simple, well-cited baseline for graph neural network research

When to avoid

• you need PyTorch support (use the companion pygcn repo or PyTorch Geometric instead)
• you need large-scale or production graph learning with active maintenance
• you need modern GNN architectures beyond GCN and Chebyshev variants

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning python graph-convolutional-networks graph-neural-networks tensorflow semi-supervised-learning node-classification citation-networks algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tkipf/gcn")