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
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.
This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151