Pattern recognition is a fundamental task in continuous sensing applications, but real-world scenarios often experience distribution shifts that necessitate learning generalizable representations for such tasks. This challenge is exacerbated with time-series data, which also exhibit inherent nonstationarity--variations in statistical and spectral properties over time. In this work, we offer a fresh perspective on learning generalizable representations for time-series classification by considering the phase information of a signal as an approximate proxy for nonstationarity and propose a phase-driven generalizable representation learning framework for time-series classification, PhASER. It consists of three key elements: 1) Hilbert transform-based augmentation, which diversifies nonstationarity while preserving task-specific discriminatory semantics, 2) separate magnitude-phase encoding, viewing time-varying magnitude and phase as independent modalities, and 3) phase-residual feature broadcasting, integrating 2D phase features with a residual connection to the 1D signal representation, providing inherent regularization to improve distribution-invariant learning. Extensive evaluations on five datasets from sleep-stage classification, human activity recognition, and gesture recognition against 13 state-of-the-art baseline methods demonstrate that PhASER consistently outperforms the best baselines by an average of 5% and up to 11% in some cases. Additionally, the principles of PhASER can be broadly applied to enhance the generalizability of existing time-series representation learning models.

翻译：模式识别是连续感知应用中的一项基本任务，但现实场景常经历分布偏移，这需要为此类任务学习泛化性表征。对于时间序列数据，这一挑战尤为严峻，因为时间序列还表现出固有的非平稳性——即统计和频谱特性随时间变化。在本工作中，我们通过将信号的相位信息视为非平稳性的近似代理，为时间序列分类的泛化表征学习提供了一个新视角，并提出了一种相位驱动的泛化表征学习框架 PhASER。该框架包含三个关键要素：1）基于希尔伯特变换的数据增强，在保持任务特异性判别语义的同时，使非平稳性多样化；2）独立的幅值-相位编码，将时变幅值和相位视为独立的模态；3）相位-残差特征广播，将二维相位特征通过残差连接与一维信号表征相融合，提供固有的正则化以改进分布不变性学习。在来自睡眠分期、人体活动识别和手势识别的五个数据集上，与13种最先进的基线方法进行的广泛评估表明，PhASER 始终优于最佳基线方法，平均提升5%，在某些情况下提升高达11%。此外，PhASER 的原理可广泛应用于增强现有时间序列表征学习模型的泛化能力。