Learning Interpretable Differentiable Logic Networks for Time-Series Classification

TL;DR

This paper extends differentiable logic networks to univariate time-series classification by converting data into vectorized features, integrating hyperparameter optimization, and demonstrating competitive accuracy with interpretability on 51 benchmarks.

Contribution

It is the first to apply DLNs to univariate TSC, using feature-based representations and joint hyperparameter optimization for improved performance.

Findings

DLNs achieve competitive accuracy on TSC benchmarks.

The approach maintains low inference cost and interpretability.

Hyperparameter search reveals insights into DLN training dynamics.

Abstract

Differentiable logic networks (DLNs) have shown promising results in tabular domains by combining accuracy, interpretability, and computational efficiency. In this work, we apply DLNs to the domain of TSC for the first time, focusing on univariate datasets. To enable DLN application in this context, we adopt feature-based representations relying on Catch22 and TSFresh, converting sequential time series into vectorized forms suitable for DLN classification. Unlike prior DLN studies that fix the training configuration and vary various settings in isolation via ablation, we integrate all such configurations into the hyperparameter search space, enabling the search process to select jointly optimal settings. We then analyze the distribution of selected configurations to better understand DLN training dynamics. We evaluate our approach on 51 publicly available univariate TSC benchmarks. The results confirm that classification DLNs maintain their core strengths in this new domain: they deliver competitive accuracy, retain low inference cost, and provide transparent, interpretable decision logic, thus aligning well with previous DLN findings in the realm of tabular classification and regression tasks.