Gdtw: A Novel Differentiable Dtw Loss For Time Series Tasks
Xiang Liu, Naiqi Li, Shu-Tao Xia
-
SPS
IEEE Members: $11.00
Non-members: $15.00Length: 00:06:47
Dynamic time warping (DTW) is one of the most successful methods that addresses the challenge of measuring the discrepancy between two series, which is robust to shift and distortion along the time axis of the sequence. Based on DTW, we propose a novel loss function for time series data called Gumbel-Softmin based fast DTW (GDTW). To the best of our knowledge, this is the first differentiable DTW loss for series data that scales linearly with the sequence length. The proposed Gumbel-Softmin replaces the simple minimization operator in DTW so as to better integrate the acceleration technology. We also design a deep learning model combining GDTW as a feature extractor. Thorough experiments over a broad range of time series analysis tasks were performed, showing the efficiency and effectiveness of our method.
Chairs:
David Luengo