Differentiable Inference of Temporal Logic Formulas

TL;DR

This paper introduces a neural network architecture for inferring Signal Temporal Logic formulas directly via gradient descent, outperforming traditional template-based methods and revealing the problem's under-determinism.

Contribution

It presents the first RNN-based approach for temporal logic inference that learns formula structure without predefined templates, enabling more flexible and effective specification learning.

Findings

Achieves comparable or better misclassification rates than existing methods.

Demonstrates the under-determinism in temporal logic inference.

Provides systematic comparison of inference methods.

Abstract

We demonstrate the first Recurrent Neural Network architecture for learning Signal Temporal Logic formulas, and present the first systematic comparison of formula inference methods. Legacy systems embed much expert knowledge which is not explicitly formalized. There is great interest in learning formal specifications that characterize the ideal behavior of such systems -- that is, formulas in temporal logic that are satisfied by the system's output signals. Such specifications can be used to better understand the system's behavior and improve design of its next iteration. Previous inference methods either assumed certain formula templates, or did a heuristic enumeration of all possible templates. This work proposes a neural network architecture that infers the formula structure via gradient descent, eliminating the need for imposing any specific templates. It combines learning of formula structure and parameters in one optimization. Through systematic comparison, we demonstrate that this method achieves similar or better mis-classification rates (MCR) than enumerative and lattice methods. We also observe that different formulas can achieve similar MCR, empirically demonstrating the under-determinism of the problem of temporal logic inference.