Spectral Propagation Graph Network for Few-shot Time Series Classification

TL;DR

The paper introduces SPGN, a novel graph network approach that models spectral relations across time series for improved few-shot classification, outperforming existing methods significantly.

Contribution

SPGN is the first to leverage spectral comparisons and propagation in graph networks for few-shot time series classification, enhancing accuracy.

Findings

SPGN outperforms state-of-the-art methods by 4-13%.

SPGN achieves around 12% and 9% improvements in cross-domain and cross-way settings.

Spectral propagation improves classification performance in few-shot TSC.

Abstract

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.