Spectral Propagation Graph Network for Few-shot Time Series Classification

no code implementations • 8 Feb 2022 • Ling Yang, Shenda Hong, Luxia Zhang

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.

Classification Time Series +2

Iterative Bilinear Temporal-Spectral Fusion for Unsupervised Representation Learning in Time Series

no code implementations • 29 Sep 2021 • Ling Yang, Shenda Hong, Luxia Zhang

First, we revisit the augmentation methods for time series of existing works and note that they mostly use segment-level augmentation derived from time slicing, which may bring about sampling bias and incorrect optimization with false negatives due to the loss of global context.

Anomaly Detection Contrastive Learning +4