# lightaime/deep_gcns_torch

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org

Repository: https://github.com/lightaime/deep_gcns_torch
Canonical: https://ross.abutalabs.com/products/deep_gcns_torch
Language: Python
License: MIT
License Family: permissive
Topics: graph-neural-networks, geometric-deep-learning, 3d-point-clouds, deep-gcns, data-mining, pytorch, computer-vision, bioinformatics, cheminformatics, social-network, science-research, deep-learning, graph-convolutional-networks
Last push: 2022-07-31T21:01:32+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2591, "days_push": 1494, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1187, forks 153 (observed 2026-08-28T04:03:55.266510+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision
- domain: deep-learning, machine-learning, computer-vision, image-processing
- platform: python
- tags: 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
- lightaime/deep_gcns_torch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.266510+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 2026-08-30T06:23:42.998134+00:00, confidence not recorded.
  - readme: https://github.com/lightaime/deep_gcns_torch (fetched 2026-08-28T04:03:55.266510+00:00, sha 8a6ec2c7483f)
- Data as of 2026-08-30T08:39:29.467469+00:00.