用频带滤波器分解时间序列，让模型解释更直观。
FLEXtime: Filterbank learning to explain time series
- 用一组带通滤波器将时序数据拆成不同频段。
- 学习最优频段组合来解释模型预测结果。
- 适合脑电、音频等难以时域解释的信号分析。
当前最先进的时序数据可解释性方法通过为每个时间步学习实例相关的显著性掩码来解释预测；然而，由于数据本身的高度复杂性，许多类型的时间序列在时域上难以解释。为此，我们提出将时序可解释性视为对可解释组成部分的显著性图，借鉴成熟的信号处理中的信号分解方法。具体地，我们提出一种新方法 FLEXtime，利用一组带通滤波器将时序数据分解为多个频率带，然后学习这些频带的组合以最优地解释模型预测。大规模评估表明，FLEXtime 在多种数据集上平均优于现有最先进可解释性方法。该方法填补了当前时序可解释性方法的重要空白，是处理如脑电图（EEG）和音频等时序数据的有力工具。代码已公开于 https://github.com/theabrusch/FLEXtime。
原文摘要 · Abstract (English)
State-of-the-art methods for explaining predictions from time series involve learning an instance-wise saliency mask for each time step; however, many types of time series are difficult to interpret in the time domain, due to the inherently complex nature of the data. Instead, we propose to view time series explainability as saliency maps over interpretable parts, leaning on established signal processing methodology on signal decomposition. Specifically, we propose a new method called FLEXtime that uses a bank of bandpass filters to split the time series into frequency bands. Then, we learn the combination of these bands that optimally explains the model's prediction. Our extensive evaluation shows that, on average, FLEXtime outperforms state-of-the-art explainability methods across a range of datasets. FLEXtime fills an important gap in the current time series explainability methodology and is a valuable tool for a wide range of time series such as EEG and audio. Code is available at https://github.com/theabrusch/FLEXtime.
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。