Graph machine learning 工具

Posted 2021-03-22 jeshy

OGB: Open Graph Benchmark

https://ogb.stanford.edu/

https://github.com/snap-stanford/ogb

OGB is a collection of benchmark datasets, data-loaders and evaluators for graph machine learning in PyTorch.

Data-loaders are fully compatible with PyTorch Geometric (PYG) and Deep Graph Library (DGL). The goal is to have an easily-accessible standardized large-scale benchmark datasets to drive research in graph machine learning.

 

Deep Graph Library (DGL)

https://www.dgl.ai/

https://github.com/dmlc/dgl

DGL works on PyTorch 0.4.1+ and MXNet nightly build

PyTorch Geometric (PYG)

https://pytorch-geometric.readthedocs.io/en/latest/

https://github.com/rusty1s/pytorch_geometric

 

PyGSP：Graph Signal Processing in Python

https://pygsp.readthedocs.io/en/stable/index.html

https://pygsp.readthedocs.io/en/stable/reference/index.html

Development: https://github.com/epfl-lts2/pygsp.git

https://github.com/wangg12/pygsp.git

 

networkx

https://pypi.org/project/networkx/

https://github.com/networkx/networkx

Website : http://networkx.github.io/

 

igraph：network analysis tools. igraph can be programmed in R, Python, Mathematica and C/C++.

https://igraph.org/

 

graph-tools，Efficient network analysis

https://graph-tool.skewed.de/

https://git.skewed.de/count0/graph-tool

https://graph-tool.skewed.de/static/doc/index.html

https://github.com/solstag/graph-tool

 

Agglomerative cluster tool (pip install agglomcluster)

https://github.com/MSeal/agglom_cluster

http://arxiv.org/pdf/cond-mat/0309508v1.pdf

 

因果关系推理，causal inference in graphs and in the pairwise settings

https://github.com/Diviyan-Kalainathan/CausalDiscoveryToolbox

https://diviyan-kalainathan.github.io/CausalDiscoveryToolbox/html/index.html

pip install cdt

Causal Discovery Toolbox: Uncover causal relationships in Python

https://arxiv.org/abs/1903.02278