Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description
Neuro-symbolic Models for Interpretable Time Series Classification using Temporal Logic Description
复制标题
DOI：
10.1109/icdm54844.2022.00072
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Ruixuan Yan;Tengfei Ma;Achille Fokoue;Maria Chang;A. Julius
中科院分区：
文献类型：
--
作者：
Ruixuan Yan;Tengfei Ma;Achille Fokoue;Maria Chang;A. Julius
现有的时间序列分类模型大多缺乏可解释性，难以检验。可解释的机器学习模型可以帮助发现数据中的模式，并为领域专家提供易于理解的见解。在这项研究中，我们提出了神经符号时间序列分类（NSTSC），神经符号模型，利用信号时序逻辑（STL）和神经网络（NN）来完成TSC任务，使用多视图数据表示，并表示该模型作为一个人类可读的，可解释的公式。在NSTSC中，每个神经元都链接到一个符号表达式，即，STL（sub）公式。因此，NSTSC的输出可以解释为类似于自然语言的STL公式，描述隐藏在数据中的时间和逻辑关系。我们提出了一个基于NSTSC的分类器，采用决策树的方法来学习公式结构，完成多类TSC任务。所提出的平滑激活函数使模型能够以端到端的方式学习。我们在来自小鼠的真实伤口愈合数据集和来自UCR时间序列库的基准数据集上测试NSTSC，证明NSTSC实现了与最先进模型相当的性能。此外，NSTSC可以生成匹配领域知识的可解释公式。
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 enable 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 domain knowledge.