pyreason VS PyNeuraLogic

Last week, we released a paper on PyReason on Arxiv. PyReason is a Python package for logical inference and designed for use with machine learning (https://github.com/lab-v2/pyreason).

Hi, sure. With this framework, you can write and train deep learning models similarly to PyTorch or TensorFlow. Although the main aim of PyNeuraLogic is on deep relational learning and it uses custom declarative language (implemented in Python). Best fitting use cases are everything where you can utilize relations. One of those use-cases that we are promoting right now is on Graph Neural Networks (GNNs), where you have relations between nodes (such as social networks, molecules). You can then utilize those relations and do regular tasks on graphs, such as link prediction, graph classification, node classification, etc. GNNs quite nicely fit the framework and its language and can be expressed just in one line (as shown in the README). The concrete use-case of PyNeuraLogic on GNNs could then be a molecule classification (example). Other use-cases could be for NLP (we have todo to write an example for it) or knowledge base completion. You could also use it like a regular framework without utilizing relations, but in that case, it might be more efficient to go with PyTorch or TensorFlow.

For an original proposal that do logic inference on Hypergraphs I am using NeuraLogic, through a Python frontend (https://github.com/LukasZahradnik/PyNeuraLogic)

I wonder if this is something the author would have enjoyed…

PyNeuraLogic – PyNeuraLogic lets you use Python to create Differentiable Logic Programs