pysignet 1.0.0

Bridge symbolic predicate logic (SymPy) and PyTorch for neuro-symbolic AI

pysignet: Logic-as-Loss for Neural Networks

pysignet is a PyTorch library that converts symbolic predicate logic expressions (written in SymPy notation) into differentiable loss functions, enabling you to train neural networks with logical constraints using First-Order Logic (FOL). It bridges symbolic reasoning and gradient-based optimization so that logical rules like implication, mutual exclusion, or quantified constraints become training signals.

Documentation: pysignet.github.io

Quick Start

Define a logical constraint in SymPy notation, map each predicate symbol to a neural network, and compile it into a differentiable loss whose gradients flow back through the logic to every model involved.

import torch
import torch.nn as nn
from pysignet import Symbol, Variable, Implies, logic_to_loss

# Define predicate symbols and FOL variables
P, Q = Symbol("P Q")
X = Variable("X")

# "For all inputs X: if P(X) then Q(X)"
expr = Implies(P(X), Q(X))

# Map symbols to neural network models
model_p = nn.Sequential(nn.Linear(10, 1), nn.Sigmoid())
model_q = nn.Sequential(nn.Linear(10, 1), nn.Sigmoid())

predicates = {
    "P": model_p,
    "Q": model_q,
}

# Compile to a loss function
logic_loss = logic_to_loss(expr, predicates)

# Training loop
x = torch.randn(32, 10)
loss = logic_loss.loss(X=x)   # Bind X to x to get a scalar loss
loss.backward()               # Gradients flow to both models

Installation

pip install pysignet

Or with Poetry:

poetry add pysignet

Key Features

• First-Order Logic: Variables, predicates with arguments, quantifiers
• Domain Quantifiers: ForAll and Exists over finite domains
• Flexible Predicates: Neural networks or deterministic functions
• Multiple T-Norms: Product, Lukasiewicz, Godel, and Mixed t-norms
• Multiple Compilers: T-norm (mode='tnorm') and LinearThresholdUnit (mode='ltu') built-in; extend via LogicCompiler
• Full PyTorch Integration: Gradients flow through all operations

Learn More

• Core Concepts: Symbols, Variables, Predicates, T-Norms, and Quantifiers
• API Reference: Full API documentation
• Custom Compilers: Implement your own logic compilation strategy
• Notebooks: Interactive examples

Development Setup

git clone https://github.com/pysignet/pysignet.git
cd pysignet
poetry install
poetry run pytest tests/

The pre-commit hook (already configured) runs tests, type checking, and linting before each commit. See CONTRIBUTING.md for the full workflow.

License

MIT License