将可解释的微分逻辑网络首次用于单变量时序分类，兼顾精度与透明性。
Learning Interpretable Differentiable Logic Networks for Time-Series Classification
- 用Catch22和TSFresh提取时序特征，转为向量输入微分逻辑网络
- 在51个公开数据集上达到竞争性准确率，推理成本低
- 首次系统搜索配置组合，揭示模型训练动态规律
微分逻辑网络（DLNs）在表格数据领域展现了高精度、可解释性和计算高效性的优势。本文首次将DLNs应用于单变量时序分类（TSC）任务，采用基于特征的表示方法，利用Catch22和TSFresh将时间序列转化为向量形式以适配DLN分类。不同于以往固定训练配置、逐项消融的研究方式，本工作将所有配置整合进超参数搜索空间，使搜索过程能联合选择最优设置，并分析所选配置的分布以理解训练动态。在51个公开的单变量时序分类基准上评估，结果表明：分类型DLNs在此新领域仍保持核心优势——具备竞争力的准确率、极低的推理开销，以及清晰可解释的决策逻辑，与表格分类/回归任务中的发现一致。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。