Registry / ai-ml / torch-geometric

torch-geometric

library2.8.0.post1pypypi✓ verified 24d ago

PyTorch Geometric (PyG) is a library built upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range of applications related to structured data. It consists of various methods for deep learning on graphs and other irregular structures, providing easy-to-use mini-batch loaders, multi-GPU support, `torch.compile` support, a large number of common benchmark datasets, and helpful transforms. It is actively maintained with frequent minor releases delivering new features and bug fixes.

ai-ml

pip install torch_geometric

github ↗package ↗homepage ↗docs ↗changelog ↗

INSTALL

IMPORT

SIG · TORCH-GEOMETRIC

torch-geometric

ai-mlpythonv2.8.0.post1

Install

8.6s avg

Import

—

Disk

121MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v2.8.0.post1 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 0.000s · 118.3MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 8.6s · import 0.000s · 117MB

121MB installed

● package 121MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Data

✓ from torch_geometric.data import Data

✗ from torch_geometric.data import Data

This example demonstrates how to create a basic graph using PyTorch Geometric's `Data` object, which is the fundamental building block for representing graphs. It defines node features and graph connectivity (edges) and then prints basic properties of the created graph.

import torch from torch_geometric.data import Data # Define an edge list (COO format: [source_nodes, target_nodes]) edge_index = torch.tensor([[0, 1, 1, 2], [1, 0, 2, 1]], dtype=torch.long) # Define node features (3 nodes, 1 feature per node) x = torch.tensor([[-1], [0], [1]], dtype=torch.float) # Create a Data object to represent the graph data = Data(x=x, edge_index=edge_index) print(data) print(f"Number of nodes: {data.num_nodes}") print(f"Number of edges: {data.num_edges}") print(f"Is undirected: {data.is_undirected()}")

Debug

Known issues

breakingPyG 2.7.0 dropped support for Python 3.9 and PyTorch versions 1.11 through 2.5. Ensure your environment uses Python >=3.10 and PyTorch >=2.6 for compatibility.

fix

Upgrade Python to 3.10 or newer, and PyTorch to 2.6 or newer. Check the official PyG installation guide for specific PyTorch/CUDA compatibility tables.

affects: >=2.7.0

gotchaInstallation of optional C++/CUDA extensions (e.g., `torch-scatter`, `torch-sparse`) is complex and requires careful matching of PyTorch and CUDA versions, often necessitating specific pre-built wheels. Mismatched versions can lead to compilation errors or runtime issues.

fix

Always refer to the official PyTorch Geometric installation instructions. Use the provided `-f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html` link, replacing `${TORCH}` and `${CUDA}` placeholders with your exact PyTorch and CUDA versions.

affects: All versions

deprecatedThe `torch_geometric.compile` utility and `MessagePassing.jittable` attribute have been deprecated. Users should migrate to `torch.compile` for model optimization.

fix

Replace usages of `torch_geometric.compile(model)` with `torch.compile(model)`. Remove `jittable=True` from `MessagePassing` layer initializations if present.

affects: >=2.6.0

breakingThe interface and implementation of `GraphMultisetTransformer` changed in PyG 2.7.0, potentially affecting existing models that use this layer.

fix

Review the updated documentation for `GraphMultisetTransformer` and adjust your model's implementation accordingly.

affects: >=2.7.0

Upgrade

Version history

2.8.0.post1latest on PyPI · released Jul 20, 2026

Audit

Dependencies

torchrequiredCore deep learning framework. PyG 2.7.0 requires PyTorch >=2.6 and is compatible up to PyTorch 2.8. Specific PyTorch versions require matching CUDA versions for GPU usage.

pyg-liboptionalProvides heterogeneous GNN operators and advanced graph sampling routines. Recommended for full feature set and performance.

torch-scatteroptionalAccelerated and efficient sparse reductions, critical for many GNN operations. Recommended for performance.

torch-sparseoptionalSparseTensor support, crucial for memory-efficient graph computations. Recommended for performance.

torch-clusteroptionalGraph clustering routines, used in certain pooling layers and graph processing tasks. Recommended for specific features.

torch-spline-convoptionalProvides SplineConv support for specialized graph convolutions. Recommended for specific GNN architectures.

Agent activity

32 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/pyg-team/pytorch_geometric ↗

packagehttps://pypi.org/project/torch-geometric/ ↗

homepagehttps://pyg.org ↗

docshttps://pytorch-geometric.readthedocs.io ↗

changeloghttps://github.com/pyg-team/pytorch_geometric/blob/master/CHANGELOG.md ↗