Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation

Page view(s)
36
Checked on Mar 10, 2025
Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation
Title:
Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation
Journal Title:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Keywords:
Publication Date:
05 May 2023
Citation:
Qiao, Z., Hu, M., Jiang, X., Suganthan, P. N., & Savitha, R. (2023). Class-Incremental Learning on Multivariate Time Series Via Shape-Aligned Temporal Distillation. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10094960
Abstract:
Class-incremental learning (CIL) on multivariate time series (MTS) is an important yet understudied problem. Based on practical privacy-sensitive circumstances, we propose a novel distillation-based strategy using a single-headed classifier without saving historical samples. We propose to exploit Soft-Dynamic Time Warping (Soft-DTW) for knowledge distillation, which aligns the feature maps along the temporal dimension before calculating the discrepancy. Compared with Euclidean distance, Soft-DTW shows its advantages in overcoming catastrophic forgetting and balancing the stability-plasticity dilemma. We construct two novel MTS-CIL benchmarks for comprehensive experiments. Combined with a prototype augmentation strategy, our framework demonstrates significant superiority over other prominent exemplar-free algorithms.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation - CNRS@CREATE
Grant Reference no. : NA
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2379-190X
Files uploaded:

File Size Format Action
icassp-2023-final.pdf 1.37 MB PDF Request a copy