ORNL / HydraGNN
Distributed PyTorch implementation of multi-headed graph convolutional neural networks
Why this job: says: neural networks; topics: machine-learning
What it does
- Multi-headed Prediction for graph and node-level properties
- Distributed Training via DDP, FSDP (v1/v2), and DeepSpeed at supercomputing scale
- Convolutional Layers as a hyperparameter
- Geometric Equivariance in convolution and prediction (EGNN, PaiNN, PNAEq, MACE, DimeNet)
- Heterogeneous Graph Learning with typed nodes, relations, and heterogeneous GPS
Get started
python -m pip install -e .- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 128
- On GitHub
- Licence
- BSD-3-Clause
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v5.0
- Released 7 months ago
- Built with
- Python
- 85% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 76% closed
- 13 still open
- Pull requests
- 436 merged
- 6 waiting
- Releases
- 4
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| tensorflow / gnn | 1,549 | yesterday | Apache-2.0 | No downloads |
| pytorch / ignite | 4,802 | 9 days ago | BSD-3-Clause | No downloads |
| JuliaGraphs / GraphNeuralNetworks.jl | 312 | yesterday | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 85%
- Shell 15%
Topics
- machine-learning
Project record
- JobAI libraries and models
- StatusListed
- Commits931
- Forks48
- Watching8
- Stars in 28 days+1
- CreatedMay 28, 2021
- First seen by usNov 7, 2026
- CheckedNov 10, 2026