Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description

TL;DR

This paper introduces NSTSC, a neuro-symbolic model combining neural networks and signal temporal logic to perform interpretable time series classification, providing human-readable formulas that reveal data patterns and domain insights.

Contribution

The paper presents a novel neuro-symbolic framework that links neurons to STL formulas, enabling end-to-end learning of interpretable models for time series classification.

Findings

Achieves comparable accuracy to state-of-the-art models.

Generates human-readable STL formulas matching domain knowledge.

Demonstrates effectiveness on real-world and benchmark datasets.

Abstract

Most existing Time series classification (TSC) models lack interpretability and are difficult to inspect. Interpretable machine learning models can aid in discovering patterns in data as well as give easy-to-understand insights to domain specialists. In this study, we present Neuro-Symbolic Time Series Classification (NSTSC), a neuro-symbolic model that leverages signal temporal logic (STL) and neural network (NN) to accomplish TSC tasks using multi-view data representation and expresses the model as a human-readable, interpretable formula. In NSTSC, each neuron is linked to a symbolic expression, i.e., an STL (sub)formula. The output of NSTSC is thus interpretable as an STL formula akin to natural language, describing temporal and logical relations hidden in the data. We propose an NSTSC-based classifier that adopts a decision-tree approach to learn formula structures and accomplish a multiclass TSC task. The proposed smooth activation functions for wSTL allow the model to be learned in an end-to-end fashion. We test NSTSC on a real-world wound healing dataset from mice and benchmark datasets from the UCR time-series repository, demonstrating that NSTSC achieves comparable performance with the state-of-the-art models. Furthermore, NSTSC can generate interpretable formulas that match with domain knowledge.