| Paper ID | MLSP-5.4 |
| Paper Title |
GDTW: A NOVEL DIFFERENTIABLE DTW LOSS FOR TIME SERIES TASKS |
| Authors |
Xiang Liu, Naiqi Li, Shu-Tao Xia, Tsinghua University, China |
| Session | MLSP-5: Machine Learning for Classification Applications 2 |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 14:00 - 14:45 |
| Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-PRCL] Pattern recognition and classification |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
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. |
