Domain Generalization via Selective Consistency Regularization for Time Series Classification

Page view(s)
28
Checked on Sep 24, 2023
Domain Generalization via Selective Consistency Regularization for Time Series Classification
Title:
Domain Generalization via Selective Consistency Regularization for Time Series Classification
Journal Title:
2022 26th International Conference on Pattern Recognition (ICPR)
Keywords:
Publication Date:
29 November 2022
Citation:
Zhang, W., Ragab, M., & Foo, C.-S. (2022). Domain Generalization via Selective Consistency Regularization for Time Series Classification. 2022 26th International Conference on Pattern Recognition (ICPR). https://doi.org/10.1109/icpr56361.2022.9956338
Abstract:
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain generalization seek to extract domain-invariant features by minimizing the discrepancy between feature distributions across all domains, disregarding inter-domain relationships. In this paper, we instead propose a novel representation learning methodology that selectively enforces prediction consistency between source domains estimated to be closely-related. Specifically, we hypothesize that domains share different class-informative representations, so instead of aligning all domains which can cause negative transfer, we only regularize the discrepancy between closely-related domains. We apply our method to time-series classification tasks and conduct comprehensive experiments on three public real-world datasets. Our method significantly improves over the baseline and achieves better or competitive performance in comparison with state-of-the-art methods in terms of both accuracy and model calibration.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151
Description:
© 2022 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.
ISBN:
978-1-6654-9063-4
Files uploaded:

File Size Format Action
domain-generalization-via-selective-consistency-regularization-for-time-series-classification.pdf 584.11 KB PDF Request a copy