Class-incremental learning on multivariate time series via shape-aligned temporal distillation
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 So...
Main Authors: | Qiao, Zhongzheng, Hu, Minghui, Jiang, Xudong, Suganthan, Ponnuthurai Nagaratnam, Savitha, Ramasamy |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/165392 |
Similar Items
-
Class-incremental learning for time series: benchmark and evaluation
by: Qiao, Zhongzheng, et al.
Published: (2024) -
Self-distillation for randomized neural networks
by: Hu, Minghui, et al.
Published: (2024) -
Minimum Cost Averaging for Multivariate Time Series Using Constrained Dynamic Time Warping: A Case Study in Robotics
by: Irati Rasines, et al.
Published: (2023-01-01) -
Can we speculate running application with server power consumption trace?
by: Li, Yuanlong, et al.
Published: (2019) -
Design of an Integrated Myocardial Infarction Detection Model Using ECG Connectivity Features and Multivariate Time Series Classification
by: Pushpam Jain, et al.
Published: (2024-01-01)