Few-shot Time Series Classification (few-shot TSC) is a challenging problem in time series analysis. It is more difficult to classify when time series of the same class are not completely consistent in spectral domain or time series of different classes are partly consistent in spectral domain. To address this problem, we propose a novel method named Spectral Propagation Graph Network (SPGN) to explicitly model and propagate the spectrum-wise relations between different time series with graph network. To the best of our knowledge, SPGN is the first to utilize spectral comparisons in different intervals and involve spectral propagation across all time series with graph networks for few-shot TSC. SPGN first uses bandpass filter to expand time series in spectral domain for calculating spectrum-wise relations between time series. Equipped with graph networks, SPGN then integrates spectral relations with label information to make spectral propagation. The further study conveys the bi-directional effect between spectral relations acquisition and spectral propagation. We conduct extensive experiments on few-shot TSC benchmarks. SPGN outperforms state-of-the-art results by a large margin in $4\% \sim 13\%$. Moreover, SPGN surpasses them by around $12\%$ and $9\%$ under cross-domain and cross-way settings respectively.
翻译:时间序列分类(few-shot TSC)在时间序列分析中是一个具有挑战性的问题。当同一类的时间序列在光谱域或不同类别的时间序列中不完全一致时,更难分类。为了解决这个问题,我们提议了一个名为Spectral Propagation 图形网络(SPGN)的新颖方法,以通过图形网络明确建模和传播不同时间序列之间的光谱关系。根据我们的知识,SPGN是第一个在不同时间序列中使用频谱比较,并涉及通过图形网络在所有时间序列中进行光谱传播,以图式网络为少发的TSC。SPGN首先使用频带过滤器扩大光谱域中的时间序列,以计算时间序列之间的频谱关系。在图形网络中,SPGN将光谱关系与标签信息结合起来,以便进行光谱传播。进一步研究传达了光谱关系获取和光谱传播之间的双向效应。我们首先使用不同频谱谱谱谱比较基准,并涉及所有时间序列的光谱谱序列的频谱谱传播。SPGN超越所有时间序列的光谱序列。SPGN将光谱序列的光谱结果分别以4+13美元和12美元左右和13美元跨方位。