Domain Generalization via Selective Consistency Regularization for Time Series Classification
This addresses domain shift in time series classification, offering a more targeted approach to improve robustness, though it is incremental in refining existing domain generalization techniques.
The paper tackles domain generalization for time series classification by proposing a method that selectively enforces prediction consistency between closely-related source domains, rather than aligning all domains, to avoid negative transfer. It shows significant improvements over baselines and achieves competitive or better performance in accuracy and model calibration on three real-world datasets.
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.