pytorch-concepts 1.0.0a1

Concept-Based Deep Learning Library for PyTorch.

🚀 Getting Started - 📚 Documentation - 💻 User guide

PyC is a library built upon PyTorch and Pytorch Lightning to easily implement interpretable and causally transparent deep learning models. The library provides primitives for layers (encoders, predictors, special layers), probabilistic models, and APIs for running experiments at scale.

The name of the library stands for both

• PyTorch Concepts: as concepts are essential building blocks for interpretable deep learning.
• $P(y|C)$: as the main purpose of the library is to support sound probabilistic modeling of the conditional distribution of targets $y$ given concepts $C$.

---

Quick Start

You can install PyC with core dependencies from PyPI:

pip install pytorch-concepts

After installation, you can import it in your Python scripts as:

import torch_concepts as pyc

Follow our user guide to get started with building interpretable models using PyC!

---

PyC Software Stack

The library is organized to be modular and accessible at different levels of abstraction:

• Conceptarium (No-code API). Use case: applications and benchmarking. These APIs allow to easily run large-scale highly parallelized and standardized experiments by interfacing with configuration files. Built on top of Hydra and WandB.
• High-level APIs. Use case: use out-of-the-box state-of-the-art models. These APIs allow to instantiate use implemented models with 1 line of code. This interface is built in Pytorch Lightning to easily standardize training and evaluation.
• Mid-level APIs. Use case: build custom interpretable and causally transparent probabilistic graphical models. These APIs allow to build new interpretable probabilistic models and run efficient tensorial probabilistic inference.
• Low-level APIs. Use case: assemble custom interpretable architectures. These APIs allow to build architectures from basic interpretable layers in a plain PyTorch-like interface. These APIs also include metrics, losses, and datasets.

---

Contributing

Contributions are welcome! Please check our contributing guidelines to get started.

Thanks to all contributors! 🧡

External Contributors

• Sonia Laguna, ETH Zurich (CH).
• Moritz Vandenhirtz, ETH Zurich (CH).

---

Cite this Library

If you found this library useful for your research article, blog post, or product, we would be grateful if you would cite it using the following bibtex entry:

@software{pycteam2025concept,
    author = {Barbiero, Pietro and De Felice, Giovanni and Espinosa Zarlenga, Mateo and Ciravegna, Gabriele and Dominici, Gabriele and De Santis, Francesco and Casanova, Arianna and Debot, David and Giannini, Francesco and Diligenti, Michelangelo and Marra, Giuseppe},
    license = {Apache 2.0},
    month = {3},
    title = {{PyTorch Concepts}},
    url = {https://github.com/pyc-team/pytorch_concepts},
    year = {2025}
}

Reference authors: Pietro Barbiero, Giovanni De Felice, and Mateo Espinosa Zarlenga.

---

Funding

This project is supported by the following organizations: