lightaime/deep_gcns_torch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1187 stars · 153 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch library implementing DeepGCNs, DeeperGCN, and GNN1000 - graph convolutional network architectures that borrow residual/dense connections and dilated convolutions from CNNs to enable very deep GCN training. It includes a GCN library plus example code for point cloud classification/segmentation, protein-protein interaction node classification, and OGB benchmarks.

Use cases

• train very deep graph convolutional networks in pytorch
• semantic segmentation of 3d point clouds
• classify point cloud models like modelnet40
• node classification on protein interaction or ogb datasets
• apply residual and dilated convolutions to graph neural networks
• reproduce deepgcn research results

When to choose

• you need proven deep GCN architectures with pretrained models
• you work on 3D point cloud segmentation or classification with PyTorch
• you want to experiment with very deep GNNs (up to 1000 layers) on OGB benchmarks

When to avoid

• you need a general-purpose GNN framework rather than specific research models
• you want actively maintained code - the last release was 2022
• you prefer TensorFlow or frameworks other than PyTorch/PyG

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision deep-learning machine-learning computer-vision image-processing python graph-neural-networks graph-convolutional-networks geometric-deep-learning 3d-point-clouds pytorch pytorch-geometric deep-gcns research-code point-cloud-segmentation node-classification linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lightaime/deep_gcns_torch")