Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator
This work addresses the challenge of automated formal specification learning for temporal sequences, which is incremental as it builds on existing neural methods for logic learning.
The paper tackles the problem of learning compact finite linear temporal logic (LTL_f) formulas from labeled traces of system behavior, proposing a neural network operator called NeuralLTL_f that scales to larger formula sizes and maintains high accuracy with noise, achieving strong performance in experiments.
Finite linear temporal logic ($\mathsf{LTL}_f$) is a powerful formal representation for modeling temporal sequences. We address the problem of learning a compact $\mathsf{LTL}_f$ formula from labeled traces of system behavior. We propose a novel neural network operator and evaluate the resulting architecture, Neural$\mathsf{LTL}_f$. Our approach includes a specialized recurrent filter, designed to subsume $\mathsf{LTL}_f$ temporal operators, to learn a highly accurate classifier for traces. Then, it discretizes the activations and extracts the truth table represented by the learned weights. This truth table is converted to symbolic form and returned as the learned formula. Experiments on randomly generated $\mathsf{LTL}_f$ formulas show Neural$\mathsf{LTL}_f$ scales to larger formula sizes than existing approaches and maintains high accuracy even in the presence of noise.