Edge representation learning library
Project description
PyTorch-Geometric Edge
PyTorch-Geometric Edge (PyGE) is a library that implements models for learning vector representations of graph edges. It is build upon the popular PyG library and allows to mix layers and models from both libraries in the same code. Note that PyGE is still under development and model APIs may change in future revisions.
Installation
Currently, we test our code using Python 3.8, but newer versions should work fine as well. We plan to extend our test suite in upcoming releases. The same applies for the PyTorch version – we currently run our tests using PyTorch 1.10.0.
For a detailed list of required packages, please take a look at the setup.py
file, where library versions are constrained.
You can install PyGE using pip:
$ pip install torch-geometric-edge
Available models
Currently, we implement the following edge-centric models:
- non-trainable node pair operators: Average, Hadamard, L1, L2
- node2edge and edge2node layers
- Line2vec
- AttrE2vec
- PairE
- Dual Hypergraph Transformation
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for torch_geometric_edge-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 00bec59ff7c0c4951fa89f06918fda04f04a6ab2245a9dd7951fe3a3b4eb1683 |
|
MD5 | f8862ab1f7d47e101ff1d1e6aa12dd80 |
|
BLAKE2b-256 | d5baa821fa9e33e687194c07a50b1bc849111d5adfc097a86038a9beb7381a9f |