Continuous Modal Logical Neural Networks: Modal Reasoning via Stochastic Accessibility

TL;DR

This paper introduces Continuous Modal Logical Neural Networks (CMLNNs), a novel framework that lifts modal reasoning to continuous manifolds using Neural SDEs, enabling structured, risk-aware, and memory-efficient neural logical reasoning across various domains.

Contribution

The paper presents Fluid Logic and LINNs, integrating modal logic into neural networks via Neural SDEs, providing structural, probabilistic, and memory advantages over traditional methods.

Findings

Neural SDEs prevent quantifier collapse and differentiate modal operators.

Modal operators act as entropic risk measures with Monte Carlo guarantees.

Framework successfully applied to epistemic, temporal, and deontic logic tasks.

Abstract

We propose Fluid Logic, a paradigm in which modal logical reasoning, temporal, epistemic, doxastic, deontic, is lifted from discrete Kripke structures to continuous manifolds via Neural Stochastic Differential Equations (Neural SDEs). Each type of modal operator is backed by a dedicated Neural SDE, and nested formulas compose these SDEs in a single differentiable graph. A key instantiation is Logic-Informed Neural Networks (LINNs): analogous to Physics-Informed Neural Networks (PINNs), LINNs embed modal logical formulas such as ($\Box$ bounded) and ($\Diamond$ visits\_lobe) directly into the training loss, guiding neural networks to produce solutions that are structurally consistent with prescribed logical properties, without requiring knowledge of the governing equations. The resulting framework, Continuous Modal Logical Neural Networks (CMLNNs), yields several key properties: (i) stochastic diffusion prevents quantifier collapse ($\Box$ and $\Diamond$ differ), unlike deterministic ODEs; (ii) modal operators are entropic risk measures, sound with respect to risk-based semantics with explicit Monte Carlo concentration guarantees; (iii)SDE-induced accessibility provides structural correspondence with classical modal axioms; (iv) parameterizing accessibility through dynamics reduces memory from quadratic in world count to linear in parameters. Three case studies demonstrate that Fluid Logic and LINNs can guide neural networks to produce consistent solutions across diverse domains: epistemic/doxastic logic (multi-robot hallucination detection), temporal logic (recovering the Lorenz attractor geometry from logical constraints alone), and deontic logic (learning safe confinement dynamics from a logical specification).