Metadata-Version: 2.4
Name: ngab
Version: 0.1.0
Summary: Noisy Graph Alignment Benchmark (NGAB) - a library for benchmarking GNNs on graph alignment tasks and generating positional encodings.
Project-URL: Homepage, https://github.com/adrien-lagesse/graph-alignment-benchmark
Project-URL: Repository, https://github.com/adrien-lagesse/graph-alignment-benchmark
Project-URL: Issues, https://github.com/adrien-lagesse/graph-alignment-benchmark/issues
Project-URL: Documentation, https://github.com/adrien-lagesse/graph-alignment-benchmark#readme
Author-email: Adrien Lagesse <contact@adrien-lagesse.io>
License-Expression: MIT
License-File: LICENSE
Keywords: Benchmark,Combinatorial Optimization,GNN,Graph Alignment,Graph Neural Networks,Graphs,Positional Encodings,Pre-training,Pytorch,Torch-Geometric
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.12
Requires-Dist: huggingface-hub>=0.35.3
Requires-Dist: jaxtyping>=0.3
Requires-Dist: numpy>=2.3
Requires-Dist: rdkit>=2025.3
Requires-Dist: safetensors>=0.6
Requires-Dist: scipy>=1.16
Requires-Dist: torch-cluster
Requires-Dist: torch-geometric>=2.6
Requires-Dist: torch-scatter
Requires-Dist: torch-sparse
Requires-Dist: torch-spline-conv
Requires-Dist: torch>=2.8
Requires-Dist: wandb>=0.21
