PythonOT/POT
Python library providing differentiable optimal transport solvers for machine learning applications including domain adaptation, GNN layers, and OT barycenters.
Not currently ranked — collecting fresh signals.
star history
POT provides a comprehensive set of solvers for optimal transport problems including exact linear OT, regularized OT (Sinkhorn), Gromov-Wasserstein, and fused variants. It offers ML-specific tools for domain adaptation, optimal transport mapping estimation, and GNN layers. The library supports multiple backends (PyTorch, Jax, TensorFlow, NumPy, CuPy) enabling differentiable computations for integration into ML pipelines.
Frequently asked
- What is PythonOT/POT?
- Python library providing differentiable optimal transport solvers for machine learning applications including domain adaptation, GNN layers, and OT barycenters.
- Is POT open source?
- Yes — PythonOT/POT is open source, released under the MIT license.
- What language is POT written in?
- PythonOT/POT is primarily written in Python.
- How popular is POT?
- PythonOT/POT has 2.8k stars on GitHub.
- Where can I find POT?
- PythonOT/POT is on GitHub at https://github.com/PythonOT/POT.